© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 44449
    Prev
    Next
    INDEX
    Explanations

    Breaking Bad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ়া
    0.75
    gaon
    0.69
    ँ
    0.68
    ット
    0.68
     maf
    0.67
     mafia
    0.66
    ymas
    0.66
    ktan
    0.65
     Fock
    0.64
    -¹
    0.64
    POSITIVE LOGITS
    л
    0.75
     can
    0.70
    ור
    0.64
     be
    0.63
    ,
    0.63
    and
    0.61
    ž
    0.60
    తు
    0.59
    żeli
    0.55
     al
    0.55
    Activations Density 0.001%

    No Known Activations