© 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. 13698
    Prev
    Next
    INDEX
    Explanations

    knees bent, Diamonds

    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
    silent
    2.56
    sign
    2.47
    s
    2.44
    IENCE
    2.41
    STRO
    2.31
    𝒐
    2.20
     altra
    2.20
    sı
    2.16
    সি
    2.12
    ség
    2.11
    POSITIVE LOGITS
    好事
    2.35
     проис
    2.33
    Појединачна
    2.28
    erat
    2.22
    үнд
    2.16
    ң
    2.15
    gart
    2.09
    woord
    2.06
    ड्या
    2.05
    RIBUTES
    2.03
    Activations Density 0.140%

    No Known Activations