© 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. 7225
    Prev
    Next
    INDEX
    Explanations

    date formats

    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
    ンス
    0.48
    jewelry
    0.44
    alloween
    0.43
     পানির
    0.42
    ড়
    0.41
     إن
    0.40
    ěž
    0.39
    도
    0.39
    țiile
    0.39
     Remington
    0.39
    POSITIVE LOGITS
     neighbouring
    0.55
     iaitu
    0.52
     haemat
    0.48
     coloured
    0.48
     Organisation
    0.47
     cosy
    0.47
     bahawa
    0.47
     aplikasi
    0.46
     organise
    0.46
     Centre
    0.46
    Activations Density 0.006%

    No Known Activations