© 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. 68998
    Prev
    Next
    INDEX
    Explanations

    shopping for

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

    quick fixes

    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
    에
    0.46
    OBI
    0.46
    %%%%%%%%%%%%%%%%
    0.45
    ре
    0.44
    impossible
    0.43
    oben
    0.43
     inadvertently
    0.43
    explored
    0.42
    exported
    0.42
    presented
    0.42
    POSITIVE LOGITS
     lateribus
    0.61
     Admissions
    0.51
     tacos
    0.50
    𝜁
    0.50
    屜
    0.49
    🔇
    0.49
     পাখ
    0.48
     Antenna
    0.47
     antennes
    0.46
     että
    0.46
    Activations Density 0.001%

    No Known Activations