© 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. 4993
    Prev
    Next
    INDEX
    Explanations

    making decisions

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

    making decisions

    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
    컵
    0.44
     ሁኔታ
    0.42
     राख
    0.42
     fuselage
    0.42
     nou
    0.41
     لوبی
    0.40
     jungle
    0.40
     claws
    0.40
    诘
    0.40
    세
    0.39
    POSITIVE LOGITS
     decisions
    1.48
     Decisions
    1.40
     decision
    1.33
     decisión
    1.32
    decision
    1.30
     decisiones
    1.24
     décisions
    1.23
     keputusan
    1.19
     decisione
    1.18
     decisão
    1.17
    Activations Density 0.119%

    No Known Activations