© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17277
    Prev
    Next
    INDEX
    Explanations

    lists and structure

    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
     fundamentos
    0.38
    ethyst
    0.37
    㳓
    0.36
     Same
    0.35
    urato
    0.35
     Affiliate
    0.35
    pounds
    0.34
     alertDialog
    0.34
    Willow
    0.34
     Withdraw
    0.34
    POSITIVE LOGITS
     sebagai
    0.43
    による
    0.43
    揖
    0.42
     ಘೋಷ
    0.41
     എത്തി
    0.41
     electron
    0.40
     као
    0.39
     musée
    0.39
    ⏤
    0.39
     späteren
    0.38
    Activations Density 0.007%

    No Known Activations