© 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. 199836
    Prev
    Next
    INDEX
    Explanations

    purchase of

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

    numbers and precision

    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
    ನೇ
    0.43
     ناز
    0.43
    chatID
    0.43
     obligatorio
    0.43
    estimating
    0.42
    ன
    0.41
    μβρίου
    0.41
    راب
    0.41
    𝒽
    0.41
    institutional
    0.40
    POSITIVE LOGITS
     laki
    0.44
     dalam
    0.44
     drie
    0.43
     Tayler
    0.43
    rik
    0.43
     terve
    0.43
     CTL
    0.41
    帀
    0.41
    ateri
    0.41
     তিনটি
    0.40
    Activations Density 0.000%

    No Known Activations