© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13044
    Prev
    Next
    INDEX
    Explanations

    sea snails and land snails

    np_acts-logits-general · gemini-2.5-flash-lite

    references to snails or snail-related terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires specifically on occurrences of “snail” (and its plural or possessive forms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ꮠ
    -2.80
    洳
    -2.64
    ſu
    -2.44
    漚
    -2.38
     anún
    -2.34
    纥
    -2.34
    ỽ
    -2.31
    窳
    -2.30
    噲
    -2.28
    좇
    -2.27
    POSITIVE LOGITS
     So
    2.56
     constitute
    2.34
     ‘
    2.28
     creando
    2.19
    );
    2.14
     tyrannical
    2.13
     
    2.09
     ?”
    2.02
     coworkers
    2.02
     Virtually
    1.99
    Activations Density 0.001%

    No Known Activations