© 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-16K
    7. 6768
    Prev
    Next
    INDEX
    Explanations

    hostile nations or liberty

    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_16k_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
    枓
    0.71
    لیفون
    0.70
    ಕ್ಸ್
    0.66
    輥
    0.65
     هستند
    0.64
     کھیلیں
    0.63
    ENCIAS
    0.63
     contratto
    0.62
    𐰚
    0.62
    蕗
    0.61
    POSITIVE LOGITS
     polity
    0.59
     countenance
    0.59
     fatally
    0.57
     dishon
    0.56
     usurp
    0.56
    {\
    0.55
     seduced
    0.55
     subjug
    0.54
     trifling
    0.54
     venge
    0.54
    Activations Density 0.023%

    No Known Activations