© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2272
    Prev
    Next
    INDEX
    Explanations

    VALUE PRO

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    ceu
    1.00
    ňa
    0.96
    qt
    0.95
    esthesia
    0.93
    𝕕
    0.92
    ța
    0.92
    prs
    0.91
    što
    0.91
    läufig
    0.91
    𝐛
    0.90
    POSITIVE LOGITS
    IG
    1.82
    ING
    1.81
    UM
    1.80
    ER
    1.78
    ES
    1.76
    IL
    1.75
    UL
    1.72
    OM
    1.71
    EL
    1.67
    IN
    1.67
    Activations Density 0.309%

    No Known Activations