© 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. 117264
    Prev
    Next
    INDEX
    Explanations

    alternatives that make

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

    breakdown of sections

    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
     a
    0.51
     Sylvia
    0.48
     hatching
    0.47
     Rover
    0.45
     Randy
    0.44
     Queen
    0.44
     ...
    0.43
     Alas
    0.43
     Gro
    0.42
     Potter
    0.42
    POSITIVE LOGITS
    췌
    0.49
    कुंड
    0.48
    httpRequest
    0.47
    iteiten
    0.46
    HTTPRequest
    0.46
     शर्ट
    0.45
    HTTP
    0.45
    군의
    0.44
     गिफ्ट
    0.43
     क्षति
    0.43
    Activations Density 0.002%

    No Known Activations