© 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. 44646
    Prev
    Next
    INDEX
    Explanations

    why, how, reasons

    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
     reports
    0.50
     in
    0.46
     continua
    0.46
    reports
    0.46
     mao
    0.44
    咸
    0.42
    african
    0.42
    ोटे
    0.41
     Reports
    0.41
    layer
    0.40
    POSITIVE LOGITS
     სახელმწიფ
    0.53
     కీల
    0.50
     JUD
    0.49
     ಸ್
    0.48
     заинтере
    0.48
    éfonos
    0.47
     ხელისუფლების
    0.46
     njia
    0.46
    ☺
    0.45
     vendeurs
    0.44
    Activations Density 0.001%

    No Known Activations