© 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. 15542
    Prev
    Next
    INDEX
    Explanations

    multi-language words

    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
    Valencia
    0.43
    ปรับ
    0.42
    𝓁
    0.42
    espec
    0.42
    𝓈
    0.41
     আঘাতে
    0.41
    Emit
    0.41
    调整
    0.41
    polarized
    0.41
    颓
    0.41
    POSITIVE LOGITS
     acesta
    0.50
     acolo
    0.48
     stein
    0.45
     komunik
    0.43
     chewed
    0.42
     zde
    0.42
     lector
    0.42
     Hinweis
    0.41
    }}_
    0.41
     Schon
    0.41
    Activations Density 0.001%

    No Known Activations