© 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. 32950
    Prev
    Next
    INDEX
    Explanations

    divergence, discontinuities, communities, little

    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
    მართ
    0.46
    rocess
    0.46
    ⊆
    0.44
    HT
    0.42
     arco
    0.42
     ಒಂದ
    0.42
    lias
    0.42
    iseries
    0.41
     fulfils
    0.41
    IV
    0.41
    POSITIVE LOGITS
    郓
    0.49
     desac
    0.46
    ag
    0.45
     зарабо
    0.44
     leaderboard
    0.44
     MacL
    0.44
     Florent
    0.44
     জরিমানা
    0.44
     jub
    0.43
     разру
    0.43
    Activations Density 0.001%

    No Known Activations