© 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. 49112
    Prev
    Next
    INDEX
    Explanations

    level of

    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
    ون
    0.96
    ים
    0.86
    る
    0.86
    на
    0.80
    ی
    0.77
    いた
    0.72
     ৩
    0.71
     lumea
    0.69
    (),
    0.66
    ా
    0.66
    POSITIVE LOGITS
     nivel
    1.27
     level
    1.24
     nivå
    1.09
    Level
    1.08
     LEVEL
    1.05
     уровнем
    1.05
     niveau
    1.05
     livello
    1.05
    level
    1.04
     düzey
    1.02
    Activations Density 0.080%

    No Known Activations