© 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. 125446
    Prev
    Next
    INDEX
    Explanations

    concluding statements and specific nouns

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

    LLM comparison and task definition

    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
     cellulaire
    0.48
    oulton
    0.46
    婺
    0.46
     mécanismes
    0.45
     Saginaw
    0.45
    내는
    0.45
    上げ
    0.43
    oreau
    0.43
     shafts
    0.43
    anners
    0.43
    POSITIVE LOGITS
     barang
    0.49
     Theor
    0.48
     द्वि
    0.48
     तु
    0.47
    崠
    0.45
     बच्चे
    0.45
     दुस
    0.44
     Litecoin
    0.43
     året
    0.43
    and
    0.42
    Activations Density 0.000%

    No Known Activations