© 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. 149684
    Prev
    Next
    INDEX
    Explanations

    legal and liability terms

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

    making a phrase or sentence

    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
     देवी
    0.53
     chromatographed
    0.52
    ニューヨーク
    0.50
     Chakrab
    0.50
     Barack
    0.47
     ўз
    0.47
     풍
    0.46
     undulating
    0.46
     顔
    0.46
     znajdują
    0.46
    POSITIVE LOGITS
    group
    0.54
    ene
    0.54
    d
    0.50
    etic
    0.49
    ed
    0.49
    content
    0.48
    de
    0.46
    text
    0.46
    ener
    0.46
    dict
    0.46
    Activations Density 0.000%

    No Known Activations