© 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. 159361
    Prev
    Next
    INDEX
    Explanations

    technical specifications

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

    avoid overly stereotypical tropes

    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
     Procter
    0.56
     Pledge
    0.54
     desempeño
    0.47
    充分
    0.47
     willingness
    0.45
    躊
    0.44
     মিলিয়ে
    0.44
     решили
    0.43
     Centennial
    0.43
     cordial
    0.42
    POSITIVE LOGITS
     grec
    0.51
    ydın
    0.51
     trữ
    0.50
     öt
    0.49
     ignores
    0.49
    κι
    0.48
     empêcher
    0.48
    sav
    0.48
    subkey
    0.47
    덮
    0.47
    Activations Density 0.000%

    No Known Activations