© 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. 144013
    Prev
    Next
    INDEX
    Explanations

    goal is publicly or centrally

    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
     ರಚ
    0.56
     ശബ്
    0.55
    Ү
    0.53
     sprem
    0.51
    )`;
    0.51
    ГЭ
    0.50
    с
    0.50
     weaken
    0.49
    ജ്
    0.49
    IfNeeded
    0.48
    POSITIVE LOGITS
    esin
    0.51
    end
    0.50
    i
    0.49
    ché
    0.49
    one
    0.46
    门
    0.45
    ffiche
    0.45
    né
    0.45
    porte
    0.44
    plicates
    0.44
    Activations Density 0.003%

    No Known Activations