© 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. 242095
    Prev
    Next
    INDEX
    Explanations

    should always, with moving, each from, make use, one for

    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
     في
    0.53
     極
    0.51
     見
    0.51
     jas
    0.50
     並
    0.49
     όχι
    0.49
     יל
    0.49
     な
    0.48
     فِي
    0.48
    アジア
    0.48
    POSITIVE LOGITS
    Assign
    0.52
     Arrangement
    0.50
    Options
    0.47
    arrangement
    0.47
    annotate
    0.46
    Clique
    0.46
    Behaviour
    0.45
    献
    0.44
    adjustable
    0.44
    Favorites
    0.44
    Activations Density 0.001%

    No Known Activations