© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 107174
    Prev
    Next
    INDEX
    Explanations

    English words or phrases

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

    attics, frequently browse, certificates often, roof insulation

    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
     a
    0.50
     Leads
    0.47
     be
    0.46
     s
    0.43
    ད
    0.41
    ས
    0.41
     h
    0.41
     న
    0.40
    先后
    0.40
    "
    0.40
    POSITIVE LOGITS
    english
    0.53
     অনেকগুলি
    0.51
    ডেম
    0.50
    キャンセル
    0.50
    یشنل
    0.49
    operatorname
    0.48
    സര്‍
    0.48
    ਗੇ
    0.48
    ůli
    0.47
     militare
    0.47
    Activations Density 0.000%

    No Known Activations