© 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. 6989
    Prev
    Next
    INDEX
    Explanations

    phishing identification

    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
    řen
    1.80
    ёв
    1.75
    naud
    1.74
    지가
    1.73
    ricted
    1.71
    пин
    1.67
    stoff
    1.63
    ق
    1.59
    pace
    1.57
    قص
    1.54
    POSITIVE LOGITS
    ENIX
    2.35
    isees
    2.12
    alanx
    2.11
    ILLIPS
    2.02
    énom
    1.96
     другому
    1.95
    Ầ
    1.95
    置いて
    1.87
     weiteres
    1.87
    fono
    1.87
    Activations Density 0.025%

    No Known Activations