© 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. 46956
    Prev
    Next
    INDEX
    Explanations

    **Core** or **liquid** feed

    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
    0.55
     rive
    0.47
    cles
    0.46
     bump
    0.44
     finding
    0.44
     marketplace
    0.44
    teenth
    0.43
     place
    0.42
     finden
    0.42
     overflowing
    0.42
    POSITIVE LOGITS
    alma
    0.48
    𝘆
    0.46
     COc
    0.44
    ﹂
    0.44
    ም።
    0.43
    taken
    0.42
    XPath
    0.42
    Yang
    0.42
    atches
    0.42
    Alma
    0.41
    Activations Density 0.001%

    No Known Activations