© 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. 189270
    Prev
    Next
    INDEX
    Explanations

    day rental

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

    washing machine

    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
     Punishment
    0.45
    ช่วยเหลือ
    0.45
    䋆
    0.45
    लीस
    0.43
     उठाया
    0.43
     رابطہ
    0.43
     ஏற்கனவே
    0.43
    сти
    0.43
    quels
    0.42
    險
    0.42
    POSITIVE LOGITS
    =”
    0.45
    re
    0.45
     composição
    0.45
    癜
    0.43
    희
    0.42
     debería
    0.42
     puffs
    0.41
     podría
    0.41
    ᠴ
    0.41
    _<
    0.41
    Activations Density 0.000%

    No Known Activations