© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8522
    Prev
    Next
    INDEX
    Explanations

    europa, Disco Elysium, yahoo

    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_13_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
    ीकृत
    2.99
    colFirst
    2.76
    ੀ
    2.75
    mfenced
    2.69
    tle
    2.64
    mpl
    2.60
    𝐦
    2.57
    tan
    2.57
    tum
    2.55
    mib
    2.53
    POSITIVE LOGITS
    ن
    2.20
    з
    1.95
    ids
    1.93
    ро
    1.85
    V
    1.85
    »
    1.84
    ads
    1.82
    ס
    1.81
     đời
    1.76
    *
    1.75
    Activations Density 0.072%

    No Known Activations