© 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. 5701
    Prev
    Next
    INDEX
    Explanations

    ™ ® ℠ LLC TM

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

    program names and trademark symbols

    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
    摖
    0.28
    ل
    0.26
    𝒈
    0.25
     Darstellung
    0.25
     Radiol
    0.25
     Benutz
    0.25
     FormData
    0.25
     Nahr
    0.24
     Bezir
    0.24
     Krankenhaus
    0.24
    POSITIVE LOGITS
    ™,
    0.49
    ®,
    0.48
    ™.
    0.47
    ™
    0.46
    ®.
    0.46
    ®
    0.45
     LLC
    0.35
    ℠
    0.34
     ™
    0.33
    TM
    0.32
    Activations Density 0.437%

    No Known Activations