© 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. 174798
    Prev
    Next
    INDEX
    Explanations

    company names and stock information

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

    explaining concepts or situations

    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
    atlar
    0.51
     ট্যাব
    0.50
    Barrel
    0.50
    '
    0.48
     Акча
    0.47
     움
    0.47
    Barn
    0.47
    ahh
    0.47
    ah
    0.45
     প্রান্ত
    0.45
    POSITIVE LOGITS
    OPH
    0.46
    亂
    0.46
    পোর্ট
    0.44
    再來
    0.43
    匯
    0.41
    reporting
    0.41
     کرسک
    0.41
    ೋಗ್ಯ
    0.41
    世界上
    0.41
    كيل
    0.40
    Activations Density 0.001%

    No Known Activations