© 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. 6776
    Prev
    Next
    INDEX
    Explanations

    continue or wait

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

    return empty or null

    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
    BERGER
    0.34
     CHLOR
    0.32
    जब
    0.32
     जेव्हा
    0.32
     TEMPERATURE
    0.31
     TRPV
    0.31
    ।)
    0.31
    婦
    0.31
     น้ํา
    0.30
    Dihydro
    0.30
    POSITIVE LOGITS
    throw
    0.40
     thì
    0.37
    ではなく
    0.37
     কিংবা
    0.36
    invalid
    0.35
     yoki
    0.35
    alert
    0.35
    goto
    0.35
     veya
    0.35
    řejmě
    0.35
    Activations Density 0.003%

    No Known Activations