© 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. 9462
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    concepts and their associated elements

    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
    actionBar
    0.40
    <0x87>
    0.39
     बेरोजगार
    0.39
    栻
    0.39
    се
    0.38
    ќ
    0.38
    рав
    0.38
    皁
    0.38
    ност
    0.38
    afio
    0.38
    POSITIVE LOGITS
     പോലും
    0.43
     utilisant
    0.41
     في
    0.41
    向け
    0.41
     faisant
    0.40
     عندهم
    0.40
     resemble
    0.39
    用に
    0.39
     végétaux
    0.39
     لو
    0.39
    Activations Density 0.039%

    No Known Activations