© 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. 240408
    Prev
    Next
    INDEX
    Explanations

    decision, exploration, and control

    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
    汶
    0.46
    ২২
    0.44
    stellungs
    0.44
    instell
    0.43
     COLLATE
    0.43
    ผลิตภัณฑ์
    0.43
    IFIER
    0.43
    忪
    0.43
    enye
    0.42
    వం
    0.41
    POSITIVE LOGITS
     reward
    0.65
     Rewards
    0.63
     rewards
    0.60
    報酬
    0.59
     rewarded
    0.58
     game
    0.56
     gameplay
    0.55
     Gameplay
    0.54
     Reward
    0.54
    Rewards
    0.54
    Activations Density 0.008%

    No Known Activations