© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72312
    Prev
    Next
    INDEX
    Explanations

    avoid long

    np_acts-logits-general · gemini-2.5-flash-lite

    motivations and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    Investing
    0.50
    褲
    0.47
    hydroxyl
    0.46
    ULS
    0.46
    ﮟ
    0.46
    alternative
    0.46
    劣化
    0.46
     Agricult
    0.46
    QCD
    0.45
    ̴
    0.45
    POSITIVE LOGITS
     zaman
    0.51
     dáng
    0.50
     seep
    0.49
     swept
    0.47
     compren
    0.47
     wrist
    0.46
     بیمار
    0.46
    āb
    0.46
     dizzy
    0.45
     çalışma
    0.45
    Activations Density 0.001%

    No Known Activations