© 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. 10477
    Prev
    Next
    INDEX
    Explanations

    opening quote and first word

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

    dialogue speaker identifier

    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
    ...
    0.49
     this
    0.48
    this
    0.47
    #
    0.44
     This
    0.44
     THIS
    0.43
     When
    0.41
    This
    0.41
     thinks
    0.40
    B
    0.40
    POSITIVE LOGITS
    faulse
    0.46
     réelle
    0.43
    Გ
    0.41
     със
    0.40
    स्टेबल
    0.40
     実
    0.39
    ्रेसेस
    0.39
    ્રોલ
    0.39
     वर्ड
    0.39
    ノ
    0.39
    Activations Density 0.013%

    No Known Activations