© 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. 66175
    Prev
    Next
    INDEX
    Explanations

    patent claims and URLs

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

    stability, fragility, effluent

    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
    f
    0.49
    often
    0.48
    Skip
    0.45
    жди
    0.44
    bhar
    0.44
     красо
    0.44
    қ
    0.43
    1
    0.43
    м
    0.43
     других
    0.43
    POSITIVE LOGITS
     län
    0.48
    tDBOutput
    0.47
     đáy
    0.46
     forested
    0.46
     제거
    0.45
     stateMutability
    0.44
     dành
    0.43
     شنا
    0.42
     슬
    0.42
     底
    0.42
    Activations Density 0.001%

    No Known Activations