© 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-65K
    7. 52082
    Prev
    Next
    INDEX
    Explanations

    explaining significance, claims, history, riddles

    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_65k_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
     مدينه
    0.54
     cemeteries
    0.53
    هاء
    0.53
    คองโก
    0.52
     ();
    0.51
     lesquels
    0.51
     unité
    0.51
     superbe
    0.51
     الداله
    0.50
     韓国
    0.50
    POSITIVE LOGITS
    weighted
    0.47
    ло
    0.43
    關於
    0.43
    적
    0.42
    Acc
    0.40
    を楽しむ
    0.39
    sided
    0.39
    Wet
    0.39
    Skip
    0.39
    ামে
    0.39
    Activations Density 0.009%

    No Known Activations