© 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-65K
    7. 55503
    Prev
    Next
    INDEX
    Explanations

    equivalent to or of

    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
    स
    0.74
    is
    0.64
    es
    0.63
     سەر
    0.62
    <unused1033>
    0.62
    س
    0.61
    en
    0.61
    ες
    0.60
    alakip
    0.59
    ೆ
    0.59
    POSITIVE LOGITS
     equivalent
    1.18
     equivalente
    1.02
    Equivalent
    0.98
     Equivalent
    0.96
     equivalents
    0.82
    equivalent
    0.75
    equival
    0.71
     equival
    0.69
     equivale
    0.67
     Equival
    0.66
    Activations Density 0.015%

    No Known Activations