© 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. 195604
    Prev
    Next
    INDEX
    Explanations

    Questa a

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

    multi-language text

    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
    yen
    0.46
    ovány
    0.44
     loaned
    0.43
    ↵↵
    0.43
    ↵
    0.42
     koup
    0.42
     zbo
    0.42
    oye
    0.41
     folio
    0.41
     KM
    0.41
    POSITIVE LOGITS
    르
    0.52
     હત્યા
    0.51
    უ
    0.49
    ጺ
    0.48
    스가
    0.48
     ਰ
    0.46
    っ
    0.46
    明的
    0.45
    𝐦
    0.45
    った
    0.45
    Activations Density 0.001%

    No Known Activations