© 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. 32657
    Prev
    Next
    INDEX
    Explanations

    of designthat dreamthere werethe site

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

    exploring reasons or qualities

    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
     গাড়ি
    0.49
     incurring
    0.48
     গাড়ী
    0.44
     incurred
    0.44
     फोटोज
    0.43
     গাড়ি
    0.42
    imageUrl
    0.42
     靴
    0.42
    cro
    0.42
     Groups
    0.41
    POSITIVE LOGITS
    ManyToMany
    0.46
     funkc
    0.45
     رئيس
    0.43
    تب
    0.43
     freien
    0.42
     درباره
    0.41
     ২০১৫
    0.41
     अनुच्छेद
    0.40
    ე
    0.40
    衔
    0.40
    Activations Density 0.000%

    No Known Activations