© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6060
    Prev
    Next
    INDEX
    Explanations

    peluche, pelaje, aggregation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    imread
    1.70
    decompose
    1.65
    有一个
    1.65
    rotation
    1.62
    蒸
    1.60
    以下
    1.60
    ificate
    1.59
    盧
    1.58
    пози
    1.58
    我有
    1.56
    POSITIVE LOGITS
    }^{-},
    0.76
    uestros
    0.74
    楽天市場
    0.74
    cyte
    0.71
     voluntarios
    0.70
    uell
    0.67
    jasama
    0.66
    Determination
    0.65
     however
    0.65
    urahan
    0.64
    Activations Density 0.098%

    No Known Activations