© 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. 132184
    Prev
    Next
    INDEX
    Explanations

    stock estimate

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

    simulating content

    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
    也就是说
    0.57
    íos
    0.45
    所谓的
    0.45
    ኋ
    0.44
     technologists
    0.44
    čili
    0.44
     કરોડ
    0.43
     Игорь
    0.43
    ذلك
    0.43
    大多数
    0.43
    POSITIVE LOGITS
     市場
    0.44
     Ladies
    0.43
     commut
    0.42
     liters
    0.41
     energetics
    0.41
     DETAILS
    0.40
     ダ
    0.40
    的時間
    0.40
     TIME
    0.40
    STO
    0.40
    Activations Density 0.001%

    No Known Activations