© 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. 192037
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by word

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

    thinking about complex situations

    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
     StandardScaler
    0.47
     cara
    0.44
     باقی
    0.44
     UserController
    0.44
     रिएक्ट
    0.44
    奭
    0.43
    漱
    0.43
     Reaction
    0.42
    lings
    0.41
     reaction
    0.41
    POSITIVE LOGITS
    рих
    0.45
    ভালো
    0.44
    positions
    0.44
    वायरमेंट
    0.43
    FROM
    0.43
    porto
    0.42
    ម
    0.42
    Pv
    0.41
    solver
    0.41
    Portal
    0.41
    Activations Density 0.000%

    No Known Activations