© 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. 138264
    Prev
    Next
    INDEX
    Explanations

    basic computer

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

    initiating sentence with "Important Considerations"

    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
     倍
    0.48
     количе
    0.47
     सत्ता
    0.47
    cantidad
    0.46
    offsetTop
    0.45
    定量
    0.44
    ানক
    0.43
     ల
    0.43
     खपत
    0.43
     نظری
    0.42
    POSITIVE LOGITS
     that
    0.51
    (&:
    0.51
    ii
    0.48
    ग
    0.48
     że
    0.46
     billi
    0.46
     arms
    0.44
    ְ
    0.43
    oper
    0.43
     entered
    0.42
    Activations Density 0.000%

    No Known Activations