© 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. 4812
    Prev
    Next
    INDEX
    Explanations

    human life and experience

    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
    m
    0.51
    in
    0.49
    type
    0.48
    ا
    0.48
    t
    0.47
    the
    0.47
    range
    0.47
    import
    0.46
    number
    0.46
    p
    0.45
    POSITIVE LOGITS
     psyche
    0.45
     persoane
    0.38
     населення
    0.36
     jiwa
    0.36
     passione
    0.35
    preneur
    0.33
    즈
    0.33
     kehidupan
    0.33
     любовь
    0.33
    Fury
    0.33
    Activations Density 0.116%

    No Known Activations