© 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. 29129
    Prev
    Next
    INDEX
    Explanations

    pull strings, off, leg, together

    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
    o
    0.68
    ه
    0.67
    and
    0.63
    e
    0.62
    i
    0.61
    d
    0.59
    is
    0.58
    light
    0.58
    a
    0.58
    k
    0.57
    POSITIVE LOGITS
     pull
    1.17
     pulling
    1.13
     pulls
    1.05
     Pull
    1.02
    Pull
    1.02
     pulled
    1.00
    pull
    0.86
     pullback
    0.82
     pux
    0.77
     тя
    0.70
    Activations Density 0.022%

    No Known Activations