© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8215
    Prev
    Next
    INDEX
    Explanations

    push back

    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_22_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
     indag
    1.15
     caveat
    1.13
     hänen
    1.13
    recurring
    1.10
    箪
    1.08
    ყო
    1.07
     seme
    1.07
    JSONArray
    1.06
     Amen
    1.05
    Quantity
    1.05
    POSITIVE LOGITS
    點
    0.89
    iego
    0.87
     غال
    0.86
     üzerinden
    0.83
    点的
    0.83
    iglio
    0.81
     manager
    0.81
     такое
    0.79
     ইসলামের
    0.79
     supposed
    0.78
    Activations Density 0.000%

    No Known Activations