© 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-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 11233
    Prev
    Next
    INDEX
    Explanations

    psychosocial, cope, hazards, bin Salman

    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
    ृत्व
    2.22
    ystycz
    2.05
    ﻯ
    1.98
    TA
    1.98
    鹉
    1.97
    ↵
    1.92
    TITLE
    1.89
     paru
    1.89
    ारीरिक
    1.87
    textarea
    1.86
    POSITIVE LOGITS
    ો
    2.86
    ución
    2.47
    aints
    2.39
     سافٹ
    2.32
    sers
    2.31
    mert
    2.29
    s
    2.26
    ավոր
    2.25
    ர்ந்த
    2.23
    silyl
    2.23
    Activations Density 0.000%

    No Known Activations