© 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. 212395
    Prev
    Next
    INDEX
    Explanations

    business and technical descriptions

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

    `.csproj` project files

    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
    3
    0.53
     blocks
    0.48
    辟
    0.48
    5
    0.46
    9
    0.46
     poser
    0.45
     retort
    0.45
     bloques
    0.45
     peculiarly
    0.44
     squat
    0.43
    POSITIVE LOGITS
    rapolation
    0.52
    .~
    0.49
    .}~\
    0.48
    presas
    0.48
    igkeit
    0.47
    ిల్లా
    0.47
    ksjon
    0.47
    größe
    0.46
    ㇁
    0.46
     выпол
    0.46
    Activations Density 0.000%

    No Known Activations