© 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. 51707
    Prev
    Next
    INDEX
    Explanations

    recipe ingredients in cups

    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
    kre
    0.47
    srcset
    0.46
    ått
    0.45
    renergic
    0.45
    ரஜன்
    0.44
    krét
    0.44
    relser
    0.43
    𒆠
    0.43
    robat
    0.42
    fler
    0.42
    POSITIVE LOGITS
     familiale
    0.45
     faculté
    0.45
     industria
    0.44
     infancia
    0.44
     اقتصاد
    0.44
    <strong>
    0.44
     civil
    0.44
     Industrie
    0.44
     colaborar
    0.43
     consequ
    0.42
    Activations Density 0.004%

    No Known Activations