© 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. 65107
    Prev
    Next
    INDEX
    Explanations

    contribution contingent

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

    bold

    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
    SH
    0.51
    phon
    0.46
     Agents
    0.46
    er
    0.44
     Advisors
    0.44
    所谓
    0.43
    భ
    0.43
    Ph
    0.43
    恐惧
    0.43
    ་
    0.43
    POSITIVE LOGITS
     basi
    0.49
     তাহারই
    0.49
     flavored
    0.49
     flavoured
    0.48
     gustaría
    0.48
     esclare
    0.48
     kaž
    0.48
     želite
    0.48
     biar
    0.48
     দেখেছিলেন
    0.47
    Activations Density 0.000%

    No Known Activations