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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 822
    Prev
    Next
    INDEX
    Explanations

    what should be

    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
    WITH
    0.44
    ろし
    0.44
     quieres
    0.44
    ﺴ
    0.44
     ongeveer
    0.43
     ekspl
    0.41
    үү
    0.41
     jambes
    0.41
     matematika
    0.41
     runnable
    0.40
    POSITIVE LOGITS
    :
    0.57
    ;
    0.47
     :-
    0.45
    estate
    0.43
    gre
    0.42
     notion
    0.42
     :,
    0.41
    neyland
    0.41
    ,:
    0.41
     :
    0.40
    Activations Density 0.002%

    No Known Activations