© 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. 172
    Prev
    Next
    INDEX
    Explanations

    ISS application

    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
    妸
    0.51
    ك
    0.50
     orche
    0.49
    '*
    0.48
    اك
    0.46
     אר
    0.46
    '।
    0.45
    Nec
    0.45
    *'
    0.45
    橑
    0.44
    POSITIVE LOGITS
     receb
    0.47
     receipt
    0.44
    読み
    0.43
    랍니다
    0.42
    (
    0.42
     favorably
    0.42
     US
    0.41
     significado
    0.41
     වශයෙන්
    0.40
     literate
    0.40
    Activations Density 0.006%

    No Known Activations