© 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. 11708
    Prev
    Next
    INDEX
    Explanations

    stranger

    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
    wake
    1.84
    outlook
    1.74
    it
    1.60
    b
    1.53
    road
    1.52
    mout
    1.52
    <0xA0>
    1.50
    or
    1.49
    he
    1.49
    atuan
    1.48
    POSITIVE LOGITS
    AllRef
    2.48
    baixo
    2.31
    RefIn
    2.18
     FormData
    2.17
    InCM
    2.16
    Invitrogen
    2.07
    RefSet
    2.07
     परिसरात
    2.04
     cidades
    2.02
    接觸
    2.01
    Activations Density 0.037%

    No Known Activations