© 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. 128021
    Prev
    Next
    INDEX
    Explanations

    disclaim liability, ensure, may

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

    platforms and features

    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
    osan
    0.46
     combs
    0.44
    痠
    0.44
     oamen
    0.43
    os
    0.43
    kä
    0.43
    gat
    0.43
     нака
    0.43
     Btn
    0.43
     alami
    0.42
    POSITIVE LOGITS
    До
    0.61
    К
    0.54
    REVIEW
    0.52
    1
    0.51
    대
    0.50
    ７
    0.49
    條
    0.49
    reported
    0.49
    РИ
    0.48
    belief
    0.48
    Activations Density 0.001%

    No Known Activations