© 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. 188997
    Prev
    Next
    INDEX
    Explanations

    planning committeeassetfixthing

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

    asking for or describing information

    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
    otipi
    0.46
    ী
    0.46
    л
    0.46
    ᐃ
    0.45
     છે
    0.45
    ді
    0.45
     після
    0.43
    ⦿
    0.43
    переди
    0.42
    ї
    0.42
    POSITIVE LOGITS
     الحل
    0.52
    Ans
    0.49
    hyd
    0.48
    dong
    0.48
    ishi
    0.48
    ansi
    0.47
     numerosos
    0.47
     numerosi
    0.46
    wara
    0.46
    PLS
    0.46
    Activations Density 0.000%

    No Known Activations