© 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. 60644
    Prev
    Next
    INDEX
    Explanations

    application ID number

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

    app identifiers and IDs

    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
     तर्क
    0.51
    rimidin
    0.49
     Peshawar
    0.49
     हल्ला
    0.47
     Хабаров
    0.46
     विलियम
    0.46
    敀
    0.46
     जवाब
    0.46
    raded
    0.45
    ahassee
    0.45
    POSITIVE LOGITS
    꿀
    0.50
    يب
    0.47
    lact
    0.46
     développ
    0.44
    গো
    0.44
     mię
    0.43
    VEN
    0.42
     inject
    0.42
    Oct
    0.42
     mnie
    0.42
    Activations Density 0.000%

    No Known Activations