© 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. 4057
    Prev
    Next
    INDEX
    Explanations

    specific recommendations or lists

    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
     言っ
    0.42
     stupidity
    0.42
     untrue
    0.41
     identidad
    0.40
     negativos
    0.39
     heterogeneity
    0.38
    🔚
    0.38
     값을
    0.38
     الداله
    0.38
     objectivity
    0.37
    POSITIVE LOGITS
     Royal
    0.53
     M
    0.42
     Greyhound
    0.41
     Solar
    0.41
     Boston
    0.41
     Howard
    0.41
     National
    0.39
     Samsung
    0.39
     Locomotive
    0.39
     Sunflower
    0.39
    Activations Density 0.311%

    No Known Activations