© 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-262K
    7. 136645
    Prev
    Next
    INDEX
    Explanations

    part of a list

    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_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
    sthe
    0.49
    íg
    0.45
    jog
    0.43
    GB
    0.43
    着
    0.42
    Viewing
    0.42
     தன்
    0.42
    $%
    0.41
    idget
    0.41
    riott
    0.41
    POSITIVE LOGITS
     Spezial
    0.45
     Parton
    0.44
     Специа
    0.43
    та
    0.42
    льность
    0.42
     Ici
    0.41
     Society
    0.40
     வேண்டும்
    0.40
    ியா
    0.40
     Laplacian
    0.40
    Activations Density 0.013%

    No Known Activations