© 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. 40-GEMMASCOPE-2-RES-262K
    7. 210428
    Prev
    Next
    INDEX
    Explanations

    multilingual examples

    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_40_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
     keres
    0.45
     browsing
    0.42
     جست
    0.41
     ஏற்பட்டது
    0.40
    browse
    0.40
    ensuche
    0.40
     пои
    0.39
     (/
    0.39
     browse
    0.38
    ကြား
    0.38
    POSITIVE LOGITS
    verlag
    0.41
    rato
    0.39
     Bazar
    0.39
     অথ
    0.38
    וע
    0.37
     grandeur
    0.37
     Larg
    0.36
     ظرف
    0.36
     సంత
    0.36
     empfehlen
    0.36
    Activations Density 0.069%

    No Known Activations