© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1602
    Prev
    Next
    INDEX
    Explanations

    technique, method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
     Schen
    2.61
    ার্ভ
    2.57
    ່ນ
    2.56
    guardo
    2.52
    odhya
    2.50
    ≃
    2.44
    ัติ
    2.43
    esley
    2.41
    bär
    2.37
     rä
    2.36
    POSITIVE LOGITS
    ৌশ
    2.76
    곸
    2.70
    ifical
    2.69
     reproduc
    2.61
    놁
    2.58
    larda
    2.56
    GetOffset
    2.56
     पत्
    2.48
    lap
    2.46
    re
    2.46
    Activations Density 0.279%

    No Known Activations