© 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. 5689
    Prev
    Next
    INDEX
    Explanations

    real-time, real-world

    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
    ungsseite
    1.74
    redient
    1.73
    ABIL
    1.70
    뺄
    1.67
    adple
    1.65
    ɾ
    1.64
    .$;
    1.62
     hardest
    1.62
     ">
    1.62
     zásob
    1.61
    POSITIVE LOGITS
    Poi
    0.80
     vagin
    0.76
    致
    0.74
    bye
    0.73
    ered
    0.72
    yai
    0.70
    ربه
    0.67
    軌
    0.66
    leigh
    0.66
    ITU
    0.65
    Activations Density 0.046%

    No Known Activations