© 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. 194684
    Prev
    Next
    INDEX
    Explanations

    problems, solutions, or technical details

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

    security risks and destruction

    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
    ವೂ
    0.51
     Comer
    0.49
     Австра
    0.47
    πί
    0.46
     Flare
    0.45
     baseman
    0.44
    倨
    0.44
     woord
    0.43
     Wochenende
    0.43
     Послед
    0.43
    POSITIVE LOGITS
    akum
    0.45
    undum
    0.45
    рики
    0.44
     mechan
    0.43
    !:
    0.43
     economic
    0.42
     retribution
    0.42
     shortages
    0.42
    solving
    0.42
     problém
    0.42
    Activations Density 0.000%

    No Known Activations