© 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. 15026
    Prev
    Next
    INDEX
    Explanations

    review tracking

    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
    ോദ
    0.48
     आजमा
    0.46
    商人
    0.46
    監
    0.45
    Muhammad
    0.44
    chner
    0.42
     इन
    0.41
    めた
    0.41
    នូវ
    0.41
    猕
    0.41
    POSITIVE LOGITS
     necessárias
    0.43
     arbeids
    0.42
     que
    0.42
     nécessaires
    0.41
     necessario
    0.41
     necesarios
    0.41
     eléctricas
    0.41
     minimize
    0.40
     sensação
    0.40
     necessity
    0.40
    Activations Density 0.001%

    No Known Activations