© 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. 12-GEMMASCOPE-2-RES-16K
    7. 7488
    Prev
    Next
    INDEX
    Explanations

    html tags

    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
    CHP
    1.34
    ča
    1.28
    2
    1.28
    1
    1.25
     sava
    1.19
    citations
    1.19
    3
    1.16
    ℓ
    1.15
    ış
    1.15
    eru
    1.15
    POSITIVE LOGITS
     Infrared
    1.68
    ontas
    1.56
     Gover
    1.55
    raviolet
    1.54
    ronectin
    1.53
    ≌
    1.52
    ارف
    1.50
    тріш
    1.49
     guineas
    1.48
    .$,
    1.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.