© 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. 169694
    Prev
    Next
    INDEX
    Explanations

    response campaign

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

    resolutions, feeding, liquid, loops, considerations, QR

    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
     快
    0.46
     シングル
    0.46
    ','"+
    0.44
     Beide
    0.44
     mehreren
    0.42
     Endpoint
    0.42
    eree
    0.42
    uchos
    0.42
    
    0.42
     电
    0.41
    POSITIVE LOGITS
    ↵
    0.63
     fung
    0.53
    नो
    0.48
    НО
    0.48
    O
    0.47
    Image
    0.47
     dedicado
    0.45
    World
    0.45
    <0xE3>
    0.44
    IUM
    0.43
    Activations Density 0.001%

    No Known Activations