© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90712
    Prev
    Next
    INDEX
    Explanations

    increasingly general distance leaps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     알아보
    0.45
     tine
    0.44
     Ohio
    0.42
     Significance
    0.41
    ....
    0.39
    当量
    0.39
    O
    0.39
    [:,
    0.39
     Alzheimer
    0.39
     Fourteenth
    0.38
    POSITIVE LOGITS
     gruppo
    0.47
    baar
    0.46
     ripet
    0.46
     rassembl
    0.46
     wyp
    0.46
    Neben
    0.45
    lessis
    0.45
     część
    0.45
    because
    0.45
     représenter
    0.44
    Activations Density 0.003%

    No Known Activations