© 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. 225161
    Prev
    Next
    INDEX
    Explanations

    locals discovered

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

    access and monitor devices

    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
     ligands
    0.52
     dumplings
    0.49
     Lukas
    0.48
    ，
    0.48
     Francesca
    0.46
     شركات
    0.46
     banknotes
    0.46
    i
    0.45
     nymphs
    0.45
     Matsuda
    0.45
    POSITIVE LOGITS
    常に
    0.47
    ѕ
    0.45
     тобто
    0.45
     pokazuje
    0.44
    接続
    0.44
    descricao
    0.44
     दमदार
    0.44
    с
    0.44
    ремя
    0.43
     ಇಂದು
    0.43
    Activations Density 0.002%

    No Known Activations