© 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. 59323
    Prev
    Next
    INDEX
    Explanations

    needlework and crafts

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

    actions and outcomes

    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
    ológico
    0.51
    োধন
    0.47
    öffent
    0.46
    তিপ
    0.43
    Quin
    0.43
    能
    0.42
    ফার
    0.42
     খেল
    0.41
    дай
    0.41
    ódigo
    0.41
    POSITIVE LOGITS
     des
    0.52
     anodes
    0.52
     dus
    0.50
     drap
    0.50
     slums
    0.49
     sarees
    0.48
    :
    0.48
    ;
    0.48
     presets
    0.48
     draped
    0.47
    Activations Density 0.000%

    No Known Activations