© 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. 16-GEMMASCOPE-2-RES-262K
    7. 106729
    Prev
    Next
    INDEX
    Explanations

    assignment operator :=

    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_16_width_262k_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
     repeal
    0.75
     giusto
    0.70
    -
    0.68
     gli
    0.65
     rápido
    0.65
     veloc
    0.64
     schimb
    0.64
     veloce
    0.64
     collusion
    0.64
     forsk
    0.63
    POSITIVE LOGITS
    :=\
    0.69
    uido
    0.64
    dataloader
    0.64
    unknown
    0.63
    U
    0.63
    ouvrir
    0.63
    pets
    0.62
    accompanied
    0.60
    getProgress
    0.60
    im
    0.59
    Activations Density 0.000%

    No Known Activations