© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 155801
    Prev
    Next
    INDEX
    Explanations

    limit quantities

    np_acts-logits-general · gemini-2.5-flash-lite

    punctuation and emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sudden
    0.53
     suddenly
    0.53
    sud
    0.46
    突然
    0.45
    </bbox>
    0.43
     mysteriously
    0.43
    alysis
    0.42
     mysterious
    0.41
     chemical
    0.41
    ">&#
    0.41
    POSITIVE LOGITS
    СП
    0.47
    REFER
    0.45
    ⚽
    0.44
    OUR
    0.44
    Government
    0.41
    POWER
    0.41
     fiel
    0.40
     அரசா
    0.40
    FUTURE
    0.40
     худож
    0.39
    Activations Density 0.000%

    No Known Activations