© 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. 1706
    Prev
    Next
    INDEX
    Explanations

    explaining myself to you

    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
    ija
    0.49
    ash
    0.47
    iron
    0.47
    ush
    0.46
    odd
    0.46
    rest
    0.45
    bis
    0.45
    2
    0.45
    realistic
    0.45
    enth
    0.44
    POSITIVE LOGITS
     crustaceans
    0.62
     snails
    0.55
     tacos
    0.55
     semigroup
    0.54
     royals
    0.54
     shrubs
    0.53
     alken
    0.52
     locust
    0.52
     cloves
    0.52
     pets
    0.51
    Activations Density 0.000%

    No Known Activations