© 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. 26732
    Prev
    Next
    INDEX
    Explanations

    the a

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

    creating or exposing systems

    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
     incluem
    0.48
    အတူ
    0.48
    ۴
    0.47
    𝗰
    0.47
    𝐚
    0.46
    ᆫ
    0.46
     குறிப்பிடத்தக்க
    0.46
     čo
    0.45
     élevée
    0.45
    󰡔
    0.45
    POSITIVE LOGITS
     తీ
    0.48
     solvent
    0.47
    '(
    0.47
    wl
    0.46
    aguan
    0.45
     fibrous
    0.44
     merc
    0.44
     শনিবার
    0.42
    stedt
    0.42
    荪
    0.42
    Activations Density 0.000%

    No Known Activations