© 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-16K
    7. 5880
    Prev
    Next
    INDEX
    Explanations

    parts of speech and relations

    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_16k_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
    atth
    0.49
    ismod
    0.49
     છો
    0.48
     мыш
    0.46
    anath
    0.45
    :"+
    0.44
    ीट
    0.44
     వ్యా
    0.44
    kada
    0.44
    ifferentiated
    0.44
    POSITIVE LOGITS
     P
    0.53
     Hill
    0.49
     Hood
    0.47
     Forrest
    0.46
     Berry
    0.45
     Lind
    0.45
     F
    0.44
     Kerr
    0.44
     scoff
    0.44
    P
    0.44
    Activations Density 0.068%

    No Known Activations