© 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. 70182
    Prev
    Next
    INDEX
    Explanations

    studied, training, consent, grove

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

    history and tradition

    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
    体验
    0.45
    رمین
    0.44
     великолеп
    0.41
     легче
    0.41
    涹
    0.41
    वटी
    0.41
    음을
    0.41
    更容易
    0.40
     മണിക്ക
    0.40
    ริญ
    0.40
    POSITIVE LOGITS
    C
    0.52
    I
    0.51
    Up
    0.50
    Uttar
    0.49
    Da
    0.47
    Me
    0.46
    ictionaries
    0.45
    A
    0.45
    Mi
    0.45
    Cr
    0.45
    Activations Density 0.001%

    No Known Activations