© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6208
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific words

    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_12_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
    er
    2.45
    evo
    2.37
    eh
    2.30
    elist
    2.03
    type
    2.02
    giene
    2.01
    e
    1.93
    ea
    1.93
    ebe
    1.92
    stag
    1.90
    POSITIVE LOGITS
    ʸ
    2.10
     якая
    1.97
    utherland
    1.94
    QRSTUVWXYZ
    1.91
     rokov
    1.91
    שור
    1.89
    </img>
    1.81
    atitis
    1.81
    менование
    1.80
    ubarb
    1.79
    Activations Density 0.606%

    No Known Activations