© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 105585
    Prev
    Next
    INDEX
    Explanations

    short phrases or clauses

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

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     기초
    0.59
     보고
    0.55
     주
    0.54
     ऑफ़
    0.53
     기본
    0.52
     Fundamental
    0.52
     갖고
    0.52
     Количество
    0.52
     ै
    0.48
     거리
    0.48
    POSITIVE LOGITS
    花
    0.47
    花的
    0.46
    ائي
    0.44
    Residents
    0.44
    رحمن
    0.43
    短
    0.43
    मण
    0.42
    שר
    0.42
    Short
    0.42
     Orsay
    0.41
    Activations Density 0.000%

    No Known Activations