© 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. 151118
    Prev
    Next
    INDEX
    Explanations

    full glass, full further

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

    goes wrong

    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
    வைக்
    0.44
    其他
    0.43
     செய்வது
    0.42
    vā
    0.42
    蟲
    0.41
     izdel
    0.41
    こちらの
    0.41
    ва
    0.40
    trashItem
    0.39
    𝒂
    0.39
    POSITIVE LOGITS
    ྡ
    0.54
     。
    0.50
    Fg
    0.48
     Blackjack
    0.48
    iad
    0.47
     minibus
    0.47
     blackjack
    0.46
    fantasy
    0.45
     fullback
    0.44
     。,
    0.44
    Activations Density 0.000%

    No Known Activations