© 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. 206334
    Prev
    Next
    INDEX
    Explanations

    services and features

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

    data analysis, research, implementation

    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
    Segundo
    0.53
     второго
    0.47
     não
    0.47
    ה
    0.46
     SECOND
    0.46
     secund
    0.46
    Acrylic
    0.44
    Stamp
    0.43
     parâmetros
    0.43
     Segunda
    0.43
    POSITIVE LOGITS
     ರೆ
    0.52
    を食べ
    0.52
     多く
    0.48
     сн
    0.47
     ንጥረ
    0.46
    snapshots
    0.46
    cells
    0.45
     അവസ്ഥ
    0.45
     体
    0.44
    bas
    0.44
    Activations Density 0.002%

    No Known Activations