© 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. 195752
    Prev
    Next
    INDEX
    Explanations

    examination and foreign languages

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

    Biomimetics, security, examination, quality

    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
     stronger
    0.50
    厂
    0.47
    having
    0.47
    strong
    0.45
    ת
    0.45
     चैंपियन
    0.44
     stories
    0.44
     business
    0.44
     driver
    0.44
     nomads
    0.43
    POSITIVE LOGITS
     sinnv
    0.56
     einfachen
    0.51
     examin
    0.50
    FreeBuf
    0.50
     exámenes
    0.50
     examen
    0.49
    قطه
    0.49
     ayudarte
    0.47
     télé
    0.46
    }+
    0.46
    Activations Density 0.000%

    No Known Activations