© 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. 24018
    Prev
    Next
    INDEX
    Explanations

    weekend forecast

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

    key 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
     predictor
    0.54
     quan
    0.46
     DETERMIN
    0.46
     Torres
    0.46
     quale
    0.45
     clue
    0.45
     hypothes
    0.45
    蔓
    0.45
     h
    0.43
     x
    0.43
    POSITIVE LOGITS
     مالک
    0.45
    блема
    0.44
    Persistence
    0.44
    Photon
    0.44
     случа
    0.43
    敢
    0.43
    ZV
    0.42
     فراهم
    0.41
    也好
    0.41
     восстановления
    0.41
    Activations Density 0.000%

    No Known Activations