Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 5410
    Prev
    Next
    INDEX
    Explanations

    default value or clear plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    Th
    1.10
    Man
    1.10
    And
    1.09
    Are
    1.06
    Look
    1.04
    T
    1.02
    Is
    0.99
    Im
    0.98
    As
    0.97
    An
    0.97
    POSITIVE LOGITS
     polymers
    0.84
     aryl
    0.83
     gourmet
    0.83
     dys
    0.82
     multit
    0.80
     at
    0.79
     emitters
    0.78
     cathodes
    0.78
     posso
    0.77
     exporting
    0.77
    Activations Density 0.000%

    No Known Activations