© 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. 50325
    Prev
    Next
    INDEX
    Explanations

    numbers and specific words

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

    formal communication content

    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
    푚
    0.50
    ખો
    0.47
    ავს
    0.47
    벧
    0.46
    کن
    0.45
    Tune
    0.43
    ڏ
    0.43
    ාව
    0.43
    חס
    0.43
    เมือง
    0.42
    POSITIVE LOGITS
    职位
    0.49
     చెర్రీ
    0.49
     indentation
    0.48
     是否
    0.47
     politicians
    0.47
     políticos
    0.46
     Integral
    0.46
     ем
    0.46
     发布
    0.46
     দৈনিক
    0.45
    Activations Density 0.000%

    No Known Activations