© 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. 5984
    Prev
    Next
    INDEX
    Explanations

    hydration

    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
    ajer
    1.95
    ąp
    1.80
    pmod
    1.71
    仃
    1.70
     Pob
    1.70
    ervation
    1.69
    zuat
    1.69
    rochemical
    1.68
    nian
    1.67
    niew
    1.67
    POSITIVE LOGITS
    迦
    0.89
    inck
    0.83
     sillas
    0.74
    angolo
    0.72
    hlas
    0.70
     begrenzt
    0.70
     сил
    0.67
    قيقة
    0.66
    スコ
    0.64
    edge
    0.63
    Activations Density 0.071%

    No Known Activations