© 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. 181410
    Prev
    Next
    INDEX
    Explanations

    actions, and consequences

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

    scaling proactively

    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
     liberación
    0.50
    堅
    0.50
     stow
    0.49
     بدي
    0.48
     دين
    0.47
    䨘
    0.47
    㣱
    0.45
     rá
    0.44
     décisions
    0.44
     sauvegard
    0.44
    POSITIVE LOGITS
     Quando
    0.60
    abulous
    0.54
     Vocal
    0.54
    ushi
    0.54
     Maximum
    0.54
    ahn
    0.53
    aln
    0.53
     Action
    0.51
    osan
    0.50
    arnell
    0.50
    Activations Density 0.001%

    No Known Activations