© 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. 146196
    Prev
    Next
    INDEX
    Explanations

    technical terms and procedures

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

    .NOTES informational tags

    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
    ↵↵
    0.52
     I
    0.48
     manufacturers
    0.44
     CDs
    0.43
     patterns
    0.43
     Hotel
    0.43
     Green
    0.42
     hotel
    0.42
     Like
    0.42
     fabrics
    0.42
    POSITIVE LOGITS
     божомолдор
    0.58
     moeil
    0.57
     glLightfv
    0.55
    럏
    0.54
    analisi
    0.53
    ⸱
    0.52
    針對
    0.49
    ᵏ
    0.49
    sulfonyl
    0.49
    “(
    0.49
    Activations Density 0.000%

    No Known Activations