© 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. 25180
    Prev
    Next
    INDEX
    Explanations

    future where

    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
    '=>'','
    0.54
     imedi
    0.51
     cristal
    0.50
     अनुरूप
    0.47
    GoAbroad
    0.47
     requiere
    0.45
     aici
    0.44
    Rigidbody
    0.44
    ынша
    0.44
     кораб
    0.44
    POSITIVE LOGITS
    I
    0.53
     billions
    0.46
     durable
    0.42
     slaughter
    0.42
    inoc
    0.42
    ج
    0.41
    goin
    0.41
     their
    0.41
     photom
    0.41
    خ
    0.41
    Activations Density 0.000%

    No Known Activations