Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 211326
    Prev
    Next
    INDEX
    Explanations

    string indexing or encryption

    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
     比
    0.43
     Fare
    0.43
    Fare
    0.41
    比
    0.40
     fare
    0.39
     revived
    0.36
    Revised
    0.35
    金
    0.35
     abband
    0.35
    Pur
    0.34
    POSITIVE LOGITS
    isecond
    0.49
     వలన
    0.41
     HUB
    0.41
    訌
    0.40
    楡
    0.40
    ünkü
    0.40
    ństwo
    0.40
     Eighteenth
    0.40
    водитель
    0.39
    로운
    0.39
    Activations Density 0.000%

    No Known Activations