© 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. 26169
    Prev
    Next
    INDEX
    Explanations

    short-term improvements

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

    encoding scheme, directly shape, automate tasks

    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
    6
    0.58
    Environment
    0.52
    5
    0.48
    multi
    0.47
    ど
    0.45
    並
    0.45
    9
    0.44
    具
    0.44
    4
    0.43
    1
    0.43
    POSITIVE LOGITS
     skóry
    0.48
     Yorkshire
    0.46
     acne
    0.46
     Acne
    0.46
     amor
    0.45
     shreds
    0.45
     fry
    0.44
     onion
    0.44
     pillows
    0.43
     blanch
    0.43
    Activations Density 0.000%

    No Known Activations