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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100937
    Prev
    Next
    INDEX
    Explanations

    force, lead, string, physics

    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
    ’
    0.41
    0.41
     někter
    0.41
     {$
    0.39
     fos
    0.39
     Tic
    0.39
     Kv
    0.39
     {#
    0.39
    стая
    0.38
     groep
    0.38
    POSITIVE LOGITS
    lyPlugin
    0.51
    ອອກ
    0.48
    Incrementor
    0.46
    ައް
    0.46
    testimonials
    0.45
     নারায়ণ
    0.45
     Леон
    0.44
    NoError
    0.44
    argaan
    0.43
    হাওয়া
    0.43
    Activations Density 0.000%

    No Known Activations