© 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. 120038
    Prev
    Next
    INDEX
    Explanations

    matters relating

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

    subjective assessment

    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
    𝚔
    0.53
     আরও
    0.48
     কমিশনের
    0.47
     ასევე
    0.46
    𝙠
    0.45
    Participants
    0.44
     avanç
    0.44
    𝗈
    0.44
    Portal
    0.44
     শন
    0.43
    POSITIVE LOGITS
    JKLMNOP
    0.48
    }[
    0.45
    valence
    0.43
    jobNumber
    0.42
    writable
    0.42
    umes
    0.41
     scare
    0.41
    GN
    0.40
    ambre
    0.40
    brev
    0.40
    Activations Density 0.001%

    No Known Activations