© 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. 133002
    Prev
    Next
    INDEX
    Explanations

    effect until

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

    learning and study

    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
    s
    0.52
    S
    0.45
    ate
    0.44
     o
    0.44
    しており
    0.44
    ot
    0.43
    ada
    0.43
     solidity
    0.41
     this
    0.41
    ies
    0.40
    POSITIVE LOGITS
     lär
    0.48
    谐
    0.48
    电机
    0.47
     гер
    0.46
     bremsstrahlung
    0.44
    ungee
    0.43
    ంబేద్
    0.43
    dishwasher
    0.42
    专门
    0.42
     niemals
    0.42
    Activations Density 0.002%

    No Known Activations