© 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. 6075
    Prev
    Next
    INDEX
    Explanations

    academic and professional titles

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

    URLs and web addresses

    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
     brib
    0.44
     それ
    0.41
    jelder
    0.39
     も
    0.39
     Länge
    0.39
    現在
    0.38
     ikke
    0.38
     Sebasti
    0.38
     同じ
    0.38
     seraient
    0.37
    POSITIVE LOGITS
    사의
    0.40
     Invitational
    0.40
    旗下
    0.40
    Guide
    0.39
    ’
    0.38
     SMART
    0.37
     Scholarship
    0.36
     Doctoral
    0.36
     PhD
    0.36
    тың
    0.35
    Activations Density 0.034%

    No Known Activations