© 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. 32238
    Prev
    Next
    INDEX
    Explanations

    travel, worthypredictions

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

    being an AI model

    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
    G
    0.59
    P
    0.58
    V
    0.52
    M
    0.52
    N
    0.51
    Г
    0.48
    ),
    0.48
    D
    0.47
    B
    0.46
    Sodium
    0.46
    POSITIVE LOGITS
     berths
    0.48
     इनके
    0.47
     ingresos
    0.46
     सफल
    0.46
     Kejriwal
    0.46
     அடுத்த
    0.46
    торой
    0.45
     survey
    0.44
     belongings
    0.44
     खरीद
    0.44
    Activations Density 0.001%

    No Known Activations