© 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. 153928
    Prev
    Next
    INDEX
    Explanations

    listing numbers and bullet points

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

    TERM (details): description

    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
     कौ
    0.42
     능
    0.41
    )_{
    0.40
    setEnabled
    0.40
     toliko
    0.40
     그런
    0.39
    度に
    0.39
     actionPerformed
    0.38
     leg
    0.38
     diligently
    0.38
    POSITIVE LOGITS
    Mem
    0.44
    Micro
    0.43
    quorum
    0.40
    灌
    0.40
    anor
    0.40
    micro
    0.39
    ква
    0.39
    management
    0.38
    潅
    0.38
    MEM
    0.38
    Activations Density 0.011%

    No Known Activations