© 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. 240404
    Prev
    Next
    INDEX
    Explanations

    relate to, based on, promise made

    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
     வருகிறார்
    0.54
     состояния
    0.53
    कालिक
    0.53
    稒
    0.52
    ស្ថានភាព
    0.51
     അവന്റെ
    0.50
     Juga
    0.49
     références
    0.47
     koszt
    0.47
     ज्यामुळे
    0.47
    POSITIVE LOGITS
    u
    0.55
    va
    0.55
    FP
    0.52
    ta
    0.50
    ya
    0.50
    de
    0.49
    ST
    0.49
    ID
    0.49
    sc
    0.48
    eta
    0.48
    Activations Density 0.005%

    No Known Activations