© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 25397
    Prev
    Next
    INDEX
    Explanations

    cards, deck

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AX
    0.36
     cerr
    0.35
     Witten
    0.35
    cerr
    0.34
     tres
    0.34
     നടത്തി
    0.34
    Button
    0.34
    ⿹
    0.34
    Lago
    0.34
     inductor
    0.33
    POSITIVE LOGITS
     deck
    2.91
     decks
    2.69
     Deck
    2.59
    Deck
    2.53
    deck
    2.47
    decks
    2.25
    デッキ
    2.22
     decking
    1.98
    덱
    1.63
     cards
    1.18
    Activations Density 0.004%

    No Known Activations