© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124510
    Prev
    Next
    INDEX
    Explanations

    measurement from point to point

    np_acts-logits-general · gemini-2.5-flash-lite

    measurement of distance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     élargies
    0.54
    소서
    0.44
     hänen
    0.43
     Biotechnol
    0.42
     Serpent
    0.41
    <unused83>
    0.41
     Snoop
    0.41
    ంబేద్
    0.41
     Giang
    0.40
    assertTrue
    0.40
    POSITIVE LOGITS
    </strong>
    0.54
    数量
    0.42
     microwave
    0.42
     amount
    0.41
     mire
    0.41
     willpower
    0.40
     recommended
    0.40
    R
    0.40
    kop
    0.40
     only
    0.39
    Activations Density 0.004%

    No Known Activations