© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9615
    Prev
    Next
    INDEX
    Explanations

    remain neutral, fixed, loyal, committed

    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_65k_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
     continuing
    0.80
     Continuing
    0.66
     blushing
    0.66
    는
    0.64
     renormal
    0.60
    циям
    0.59
    庿
    0.59
    他
    0.58
    继续
    0.58
    まだまだ
    0.58
    POSITIVE LOGITS
    ين
    0.79
    el
    0.73
    et
    0.71
    ap
    0.70
    un
    0.66
    stay
    0.66
    at
    0.65
    as
    0.65
    ar
    0.63
    stays
    0.63
    Activations Density 0.024%

    No Known Activations