© 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. 22-GEMMASCOPE-RES-131K
    7. 27398
    Prev
    Next
    INDEX
    Explanations

    hex codes and identifiers

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

    The neuron is detecting two-letter clusters of consonants (adjacent consonants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ᕱ
    -2.53
    荭
    -2.48
    倣
    -2.25
    鉝
    -2.22
    an
    -2.22
    dition
    -2.22
    啬
    -2.19
    晸
    -2.17
    省市镇
    -2.16
     polecam
    -2.14
    POSITIVE LOGITS
    2
    3.52
    3
    3.13
    9
    2.84
    At
    2.75
    From
    2.63
    If
    2.61
    This
    2.59
    By
    2.58
    section
    2.52
    However
    2.52
    Activations Density 0.034%

    No Known Activations