© 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. 109894
    Prev
    Next
    INDEX
    Explanations

    adjust your

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

    mechanical keyboard, JavaScript, Angels, Efficiency

    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
     entrevistas
    0.46
    ኡ
    0.46
    াজা
    0.45
     moléculas
    0.45
     интервью
    0.44
     ওঠা
    0.44
    愉
    0.44
     выступи
    0.44
     직
    0.43
     সন
    0.42
    POSITIVE LOGITS
    COMPONENT
    0.41
    Dates
    0.40
     Komponenten
    0.40
    رمی
    0.40
     mourning
    0.40
     Brewers
    0.40
     galore
    0.40
    શે
    0.39
     gos
    0.38
     concerned
    0.38
    Activations Density 0.000%

    No Known Activations