© 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. 219916
    Prev
    Next
    INDEX
    Explanations

    assessing conditions and consequences

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

    lost things, future, changes

    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
    하는
    0.52
    슐
    0.52
    为什么要
    0.52
    얌
    0.50
     뭐
    0.50
    లు
    0.49
    뭐
    0.48
    莓
    0.48
    瑚
    0.48
    બર
    0.47
    POSITIVE LOGITS
    <0x0D>
    0.53
     km
    0.48
     perd
    0.46
     inv
    0.45
     kaybed
    0.45
    performed
    0.45
     unable
    0.44
     performed
    0.44
    ;
    0.44
    Grad
    0.44
    Activations Density 0.001%

    No Known Activations