© 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. 14817
    Prev
    Next
    INDEX
    Explanations

    Opt Express

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

    MODE followed by separators

    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
    ukiyoe
    0.25
     ഉത്സ
    0.23
     merveille
    0.22
    𝚆
    0.22
     épars
    0.22
     rayonnement
    0.22
     ahuv
    0.22
     pomiesz
    0.22
    źć
    0.22
    لیفون
    0.21
    POSITIVE LOGITS
    '
    0.20
    PRO
    0.18
    en
    0.17
     Hiz
    0.17
    ymen
    0.17
     Publications
    0.16
    。
    0.16
    i
    0.16
    The
    0.16
     General
    0.16
    Activations Density 0.039%

    No Known Activations