© 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. 186377
    Prev
    Next
    INDEX
    Explanations

    data, insights, decisions

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

    initial stages

    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
    =@
    0.50
    Ricardo
    0.49
    ח
    0.49
    unlike
    0.46
    áf
    0.46
    hasta
    0.45
    ת
    0.45
    אה
    0.45
    Ро
    0.44
    Ар
    0.44
    POSITIVE LOGITS
     decisions
    0.43
    rische
    0.42
     स्केल
    0.42
    更容易
    0.41
     decision
    0.41
     permutation
    0.40
    很多的
    0.40
    边的
    0.40
     Considerations
    0.39
     মিথ্যা
    0.39
    Activations Density 0.001%

    No Known Activations