© 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. 79188
    Prev
    Next
    INDEX
    Explanations

    research, access, engineering, gallery, characteristics

    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
    ჲ
    0.52
    .}
    0.47
    .
    0.46
    劵
    0.46
    afi
    0.45
     ಭಯ
    0.45
    েইল
    0.44
    یکا
    0.43
    ę
    0.43
    .`
    0.43
    POSITIVE LOGITS
     Sier
    0.48
     আরে
    0.45
    es
    0.45
     따라
    0.45
     billion
    0.45
     dioxide
    0.42
     tilts
    0.42
     solvers
    0.41
     оса
    0.41
     Sander
    0.40
    Activations Density 0.000%

    No Known Activations