© 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. 95852
    Prev
    Next
    INDEX
    Explanations

    listing ideas, friendships, or articles

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

    introduces elaboration

    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
    蝌
    0.47
    ॉन
    0.47
    नातील
    0.46
    ຂອງ
    0.45
     अस्वी
    0.44
     জাতিসংঘের
    0.44
     स्थानांतर
    0.44
    鐟
    0.44
    aría
    0.43
     সন্ন
    0.43
    POSITIVE LOGITS
    كز
    0.58
     Azad
    0.46
     ins
    0.46
     eventful
    0.46
    ស
    0.46
     ملي
    0.46
     تكون
    0.45
     olyan
    0.45
     ২০২০
    0.44
     لي
    0.44
    Activations Density 0.000%

    No Known Activations