© 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. 110361
    Prev
    Next
    INDEX
    Explanations

    specific contexts and entities

    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
     (
    0.52
     oryg
    0.49
    ،
    0.46
    ፣
    0.45
     fragmentary
    0.44
     sezione
    0.44
     Oph
    0.43
    ，
    0.43
     foglie
    0.43
     $(
    0.42
    POSITIVE LOGITS
    ke
    0.50
    ynı
    0.45
    entionally
    0.45
    ociação
    0.45
    aj
    0.45
    ho
    0.45
    贊
    0.44
    ust
    0.44
    াবেন
    0.43
    ührt
    0.43
    Activations Density 0.005%

    No Known Activations