© 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. 127613
    Prev
    Next
    INDEX
    Explanations

    financial terms and punctuation

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

    your personal brand

    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
    m
    0.69
    myth
    0.50
     лишь
    0.47
    vand
    0.46
     கடற்க
    0.46
    tests
    0.46
    ют
    0.45
    يش
    0.45
    ந்த
    0.44
    mär
    0.44
    POSITIVE LOGITS
    𝑐
    0.50
    䄸
    0.45
    朔
    0.41
     Studien
    0.41
     الزاويه
    0.41
     경영
    0.41
     ორგანო
    0.41
    windigkeit
    0.40
    InitFlag
    0.40
     incontro
    0.40
    Activations Density 0.004%

    No Known Activations