© 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-65K
    7. 1569
    Prev
    Next
    INDEX
    Explanations

    key phrases

    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_65k_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
    ি
    0.51
     chest
    0.46
    athyroid
    0.45
    ног
    0.44
    requent
    0.43
    MACHINE
    0.43
    ำ
    0.43
     forehead
    0.43
    ニング
    0.43
     roughly
    0.42
    POSITIVE LOGITS
    rowadz
    0.50
    elere
    0.48
     simples
    0.46
    އ
    0.46
     sanciones
    0.45
     possibilidade
    0.44
    ({})
    0.44
     sanc
    0.43
     Epi
    0.43
     telle
    0.42
    Activations Density 0.000%

    No Known Activations