© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11413
    Prev
    Next
    INDEX
    Explanations

    TATAI, Rights, seek, swinging

    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
    ﻑ
    2.97
    eq
    2.91
    arden
    2.75
    язку
    2.55
    valuer
    2.52
    igenschaft
    2.51
    이스
    2.50
    evi
    2.50
    Riemann
    2.49
    irection
    2.48
    POSITIVE LOGITS
    ra
    3.32
    r
    3.14
    র
    3.06
    र
    3.05
    rang
    2.84
    न
    2.78
    り
    2.76
    namento
    2.75
    譽
    2.75
    ंगन
    2.70
    Activations Density 0.001%

    No Known Activations