© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143404
    Prev
    Next
    INDEX
    Explanations

    planning, company activities, He climbed, extracts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.48
     to
    0.45
    Diss
    0.44
    Second
    0.44
     compass
    0.44
    |
    0.42
    is
    0.42
    Santiago
    0.42
    .
    0.42
     at
    0.41
    POSITIVE LOGITS
    devDependencies
    0.47
    )$\
    0.46
    Khokhlov
    0.46
    addassa
    0.46
    checkable
    0.45
     grinned
    0.45
    ),],
    0.45
     вікі
    0.44
    䢍
    0.44
    <unused1163>
    0.44
    Activations Density 0.010%

    No Known Activations