© 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. 47049
    Prev
    Next
    INDEX
    Explanations

    increase productivity

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

    behavioral planning speed

    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
    lossen
    0.57
    lym
    0.53
    nity
    0.49
    lstm
    0.47
    releases
    0.47
    ritos
    0.46
    ])).
    0.46
    niki
    0.46
    <<<<
    0.45
    nicima
    0.45
    POSITIVE LOGITS
     o
    0.50
    бе
    0.48
     Effect
    0.46
     threshold
    0.46
    झ
    0.46
    сё
    0.45
     Exponential
    0.45
     interpolation
    0.45
     conducteur
    0.44
    人
    0.44
    Activations Density 0.000%

    No Known Activations