© 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. 3747
    Prev
    Next
    INDEX
    Explanations

    against my guidelines

    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
    کان
    2.65
    驁
    2.53
     subnet
    2.49
     جاي
    2.45
    ग्विजय
    2.37
    ূনতম
    2.30
    न्द्रीय
    2.27
    㜌
    2.27
     سونے
    2.26
    ཇ
    2.26
    POSITIVE LOGITS
     ContentView
    2.46
    herd
    2.16
    ా
    2.09
    兮
    2.02
     spoilt
    2.02
    ும்ப
    2.01
    ராட்ச
    2.01
    Fourth
    1.99
    세를
    1.97
    Opp
    1.92
    Activations Density 0.128%

    No Known Activations