© 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-16K
    7. 11833
    Prev
    Next
    INDEX
    Explanations

    Japanese characters, numbers, directions

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

    instructions, advice, or descriptions

    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_16k_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
    ак
    0.46
    ीय
    0.43
    ани
    0.43
    یسی
    0.42
    ет
    0.42
    貅
    0.42
    ем
    0.41
    ит
    0.41
    ině
    0.41
    PRS
    0.41
    POSITIVE LOGITS
     Interactions
    0.46
    <strong>
    0.45
    zb
    0.44
     interfacing
    0.44
     eastbound
    0.44
     buiten
    0.43
     prioritize
    0.42
     Sakurai
    0.42
     southbound
    0.41
     Assass
    0.41
    Activations Density 0.013%

    No Known Activations