© 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. 14505
    Prev
    Next
    INDEX
    Explanations

    character names

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

    character names and actions

    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
     পূর্ববাংলা
    0.49
    duled
    0.47
    तोंडा
    0.43
    <unused90>
    0.42
    是一種
    0.42
    𒐪
    0.41
     വിവിധ
    0.41
    ഴിലാ
    0.40
     overseen
    0.40
     предусматри
    0.40
    POSITIVE LOGITS
     و
    0.49
     and
    0.48
    บ
    0.47
    、
    0.46
    จ
    0.45
    zinho
    0.44
    ና
    0.42
    의
    0.42
     bout
    0.42
     પાસે
    0.42
    Activations Density 0.037%

    No Known Activations