© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 57429
    Prev
    Next
    INDEX
    Explanations

    arrival at times history tells

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

    querying multiple services

    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
    <0x9F>
    0.43
    ایر
    0.43
    sequences
    0.42
    <0x0D>
    0.42
     者
    0.42
    </tr>
    0.41
    ;
    0.39
    妑
    0.39
    etta
    0.39
     mills
    0.39
    POSITIVE LOGITS
     torneo
    0.51
    ペース
    0.50
    एफ
    0.49
    lico
    0.49
    สามารถ
    0.49
     buona
    0.47
     nello
    0.47
    Closest
    0.47
    G
    0.46
     comprov
    0.46
    Activations Density 0.000%

    No Known Activations