© 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. 5324
    Prev
    Next
    INDEX
    Explanations

    nature, method, blood, provided, car, rem

    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
     семья
    0.52
    ă
    0.48
     परिवार
    0.45
     가족
    0.44
     עם
    0.43
     사람
    0.42
     дія
    0.41
     ชีวิต
    0.41
     새
    0.41
    textColour
    0.41
    POSITIVE LOGITS
    >.
    0.44
    ponenten
    0.41
     rhino
    0.39
    nemonic
    0.39
    <0x0D>
    0.39
     fün
    0.38
     heron
    0.37
    ;.
    0.36
     perturbed
    0.36
     concomit
    0.36
    Activations Density 0.080%

    No Known Activations