© 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. 91363
    Prev
    Next
    INDEX
    Explanations

    making certain things

    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
    ~~
    0.51
    <unused84>
    0.50
    ona
    0.49
    দের
    0.48
     soirée
    0.48
     conservatory
    0.47
    বার
    0.46
    ài
    0.46
     apoptosis
    0.46
     @@
    0.46
    POSITIVE LOGITS
     дели
    0.46
    Hö
    0.45
     педагоги
    0.43
     яку
    0.42
     Aufbau
    0.42
     ис
    0.41
     регули
    0.41
     территория
    0.41
    DESIGN
    0.40
     важли
    0.40
    Activations Density 0.001%

    No Known Activations