© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46552
    Prev
    Next
    INDEX
    Explanations

    contrasts and specific topics

    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
     Tenants
    0.52
     Compton
    0.47
     tenants
    0.46
     ሞ
    0.46
     conglomer
    0.43
    萸
    0.43
     டாக
    0.42
     amid
    0.42
    ന്ത്യ
    0.42
     excre
    0.42
    POSITIVE LOGITS
    age
    0.55
    tze
    0.51
    <0x80>
    0.49
    count
    0.48
    player
    0.47
    ld
    0.46
    can
    0.46
    r
    0.45
    cv
    0.44
    terer
    0.44
    Activations Density 0.006%

    No Known Activations