© 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. 184544
    Prev
    Next
    INDEX
    Explanations

    mobile, full, contemplating, tft

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

    identify market segments

    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
    melding
    0.57
    oises
    0.52
    輔
    0.51
    бер
    0.50
    тери
    0.49
    терна
    0.47
    मां
    0.46
    corre
    0.46
    罵
    0.46
    метр
    0.46
    POSITIVE LOGITS
     doh
    0.44
    😒
    0.44
     นิด
    0.42
     Would
    0.42
    ‌پ
    0.41
     সামান্য
    0.41
    <_
    0.41
    เพียง
    0.40
     gitt
    0.40
     gewährle
    0.39
    Activations Density 0.000%

    No Known Activations