© 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. 150942
    Prev
    Next
    INDEX
    Explanations

    company actions

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

    CUDA remains, toxins and, respond, Mentimeter calculates

    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
    티브
    0.52
    어를
    0.47
    땄
    0.46
     ανάπτυ
    0.45
    웠
    0.45
     necesitamos
    0.44
     consultez
    0.44
    Ᏹ
    0.44
    𠃍
    0.44
    鈮
    0.44
    POSITIVE LOGITS
     UK
    0.54
    0.50
    seh
    0.49
    ator
    0.49
    KH
    0.45
    complete
    0.45
    /
    0.45
     UCL
    0.44
    has
    0.44
     brothers
    0.44
    Activations Density 0.008%

    No Known Activations