© 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. 137217
    Prev
    Next
    INDEX
    Explanations

    lists and categorizations

    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
    t
    0.47
    一
    0.47
    1
    0.44
    ט
    0.44
    币
    0.44
    те
    0.43
    c
    0.43
    地
    0.43
    闿
    0.43
    essentially
    0.43
    POSITIVE LOGITS
     hydrocarbons
    0.43
     híbr
    0.42
     Rockies
    0.42
     tulips
    0.41
     clauses
    0.41
     hemi
    0.41
     inconvén
    0.40
     wrongs
    0.40
     amores
    0.40
     meraih
    0.40
    Activations Density 0.001%

    No Known Activations