© 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. 83727
    Prev
    Next
    INDEX
    Explanations

    debris needs, punch one, huge expense, withdrawal symptoms

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

    what follows an explanation

    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
    ENGLISH
    0.48
     richied
    0.48
    IP
    0.45
     curioso
    0.45
     कठिना
    0.45
     livello
    0.44
    繳
    0.43
     historical
    0.43
    0.43
     metropolitan
    0.42
    POSITIVE LOGITS
     హైదర్
    0.50
    fühl
    0.50
     वक्त
    0.48
    als
    0.47
    äär
    0.47
    鲟
    0.47
    úcar
    0.47
    })-(\
    0.46
    dés
    0.46
    igenes
    0.46
    Activations Density 0.000%

    No Known Activations