© 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. 204524
    Prev
    Next
    INDEX
    Explanations

    connecting items with context

    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
    Bear
    0.44
    Bottle
    0.43
     couverts
    0.43
    1
    0.42
     Bear
    0.42
     ਟ
    0.41
    Transform
    0.40
     پوش
    0.39
     Ñ
    0.38
     cover
    0.38
    POSITIVE LOGITS
     તેમની
    0.49
    ஷன்
    0.48
     Баскетбол
    0.46
    сна
    0.46
    वं
    0.46
    між
    0.45
    🕓
    0.45
    து
    0.45
    దం
    0.45
    ять
    0.45
    Activations Density 0.002%

    No Known Activations