© 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-262K
    7. 123774
    Prev
    Next
    INDEX
    Explanations

    dealing with proficiencies

    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_262k_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
     as
    0.49
     belly
    0.49
     ple
    0.47
     sky
    0.46
     TT
    0.45
    0.44
     X
    0.43
     No
    0.43
     Hell
    0.42
     sin
    0.42
    POSITIVE LOGITS
    ી
    0.55
    GALAD
    0.54
    ЕВ
    0.54
    ва
    0.53
     инвести
    0.53
    agamanam
    0.52
    𒋗
    0.52
    یم
    0.50
    ية
    0.49
    atorii
    0.49
    Activations Density 0.005%

    No Known Activations