© 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. 31-GEMMASCOPE-2-RES-262K
    7. 47172
    Prev
    Next
    INDEX
    Explanations

    emerald green

    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/layer_31_width_262k_l0_medium
    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
    לי
    0.48
     baat
    0.47
     Zust
    0.45
    ོན་
    0.45
     స్థితి
    0.45
    SE
    0.44
    㶲
    0.43
     ట్ర
    0.42
    platz
    0.42
    懈
    0.42
    POSITIVE LOGITS
     condemns
    0.46
     winners
    0.44
     achieves
    0.41
    eleron
    0.40
     herbicides
    0.40
     immunology
    0.40
     recommends
    0.39
     हज़ार
    0.39
     adds
    0.38
    winners
    0.38
    Activations Density 0.003%

    No Known Activations