© 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. 7999
    Prev
    Next
    INDEX
    Explanations

    finding followed by description

    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
     vag
    0.50
     furious
    0.49
     cynicism
    0.46
     सो
    0.43
     pessimism
    0.43
    流畅
    0.43
    รง
    0.42
    纹
    0.42
    充满
    0.41
     납
    0.41
    POSITIVE LOGITS
    atamente
    0.47
    ivre
    0.46
    Yun
    0.45
    glichkeiten
    0.45
     múlt
    0.45
     outcomes
    0.41
    ind
    0.41
    rekken
    0.41
    𝒈
    0.41
    Means
    0.40
    Activations Density 0.007%

    No Known Activations