© 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. 163274
    Prev
    Next
    INDEX
    Explanations

    built-in mic and audio

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

    underground electronic music

    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
    ᴺ
    0.58
    дома
    0.52
    骓
    0.49
     manu
    0.48
    鑷
    0.48
     kilomet
    0.46
     Пу
    0.46
    ਾਵ
    0.46
     Fabi
    0.44
    让她
    0.43
    POSITIVE LOGITS
    sulf
    0.48
     were
    0.48
    udy
    0.47
     EDTA
    0.47
    uding
    0.47
    ampton
    0.46
    }$;
    0.46
    ystem
    0.46
     you
    0.46
    eds
    0.45
    Activations Density 0.001%

    No Known Activations