© 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. 3580
    Prev
    Next
    INDEX
    Explanations

    differenza

    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
     the
    2.17
    1
    2.03
    1.94
     this
    1.92
    ers
    1.86
    2
    1.78
    re
    1.78
     close
    1.77
    3
    1.73
     new
    1.73
    POSITIVE LOGITS
    okatokat
    4.72
    녃
    4.37
    𒀖
    4.32
     kahelar
    4.25
    梅里尼亚克
    4.24
    𒄖
    4.23
     Pusenkoff
    4.22
    <unused1324>
    4.22
     SIINFE
    4.20
    <unused1322>
    4.19
    Activations Density 0.008%

    No Known Activations