© 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. 134664
    Prev
    Next
    INDEX
    Explanations

    UK or Davis, asking for

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

    performance and skill evaluation

    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
     Knitting
    0.49
     discuter
    0.46
    🛳
    0.45
     Vinyl
    0.45
     וח
    0.45
     ஸ்ட
    0.45
     जिसे
    0.44
    蒺
    0.44
    🚥
    0.44
     ترمیم
    0.44
    POSITIVE LOGITS
    ols
    0.49
    l
    0.45
    ak
    0.43
    );//
    0.43
    tmp
    0.42
    ራል
    0.41
    ക്കിയത്
    0.41
    izations
    0.41
     violators
    0.40
    equals
    0.40
    Activations Density 0.001%

    No Known Activations