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. 8975
    Prev
    Next
    INDEX
    Explanations

    language keywords

    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
    }/${
    0.38
    ༢
    0.38
    บาย
    0.37
    柘
    0.37
    മം
    0.36
    跇
    0.35
    大师
    0.35
     employeeService
    0.35
    娍
    0.35
    ിക്കാം
    0.35
    POSITIVE LOGITS
    /*
    0.67
     public
    0.55
    public
    0.52
     /*
    0.46
    finally
    0.45
    protected
    0.44
     finally
    0.43
     finalmente
    0.41
     final
    0.40
    final
    0.38
    Activations Density 0.000%

    No Known Activations