© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79808
    Prev
    Next
    INDEX
    Explanations

    https links and code comments

    np_acts-logits-general · gemini-2.5-flash-lite

    bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    it
    0.48
    EMPT
    0.46
     (%
    0.45
    il
    0.44
    ATTRIBUTE
    0.43
    NF
    0.43
    s
    0.43
    FUNCTION
    0.42
     ВИ
    0.42
    );
    0.41
    POSITIVE LOGITS
    通
    0.53
     Speedway
    0.52
     playoff
    0.49
    伦敦
    0.48
     एक्सचेंज
    0.48
    加
    0.48
    移
    0.47
    ర్కొ
    0.46
    ान्स
    0.46
    海岸
    0.46
    Activations Density 0.000%

    No Known Activations