© 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. 62787
    Prev
    Next
    INDEX
    Explanations

    symbol or logo

    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
    p
    0.87
     outliers
    0.77
     संख्याओं
    0.69
     റ
    0.69
    y
    0.69
     sayings
    0.68
     செல்லும்
    0.68
     tensor
    0.66
     powied
    0.66
     silos
    0.66
    POSITIVE LOGITS
    0
    1.00
    <0x80>
    0.91
     bych
    0.65
    ized
    0.62
    amanho
    0.62
    <0xA2>
    0.60
    badges
    0.60
    вав
    0.60
    3
    0.60
    atorul
    0.59
    Activations Density 0.026%

    No Known Activations