© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21214
    Prev
    Next
    INDEX
    Explanations

    Sten- compounds

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

    the surname "Stenberg" and variants, along with related terms like "stencil".

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

    The neuron fires on any token containing the character sequence “sten.”

    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
    ↵↵
    -2.98
    踽
    -2.58
    there
    -2.36
     situa
    -2.20
     Ejercicio
    -2.14
    料
    -2.14
     has
    -2.11
    槼
    -2.06
     смогут
    -2.06
    (\%)
    -2.06
    POSITIVE LOGITS
    1
    2.97
    ༛
    2.89
    𖣔
    2.69
    哙
    2.48
    ⍢
    2.45
    翆
    2.38
    D
    2.34
    がっ
    2.30
    skjaer
    2.30
    丝毫
    2.30
    Activations Density 0.006%

    No Known Activations