© 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. 164437
    Prev
    Next
    INDEX
    Explanations

    descriptive texts

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

    logged in

    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
     gelas
    0.58
     所以
    0.57
     hamilton
    0.56
     arriver
    0.55
     parmes
    0.55
     刘
    0.55
     来
    0.54
     menambah
    0.54
     來
    0.54
     primeras
    0.53
    POSITIVE LOGITS
    aerial
    0.68
    the
    0.59
    Aerial
    0.56
    immobil
    0.55
    although
    0.54
    congestion
    0.52
    chronic
    0.52
    equity
    0.51
    appropri
    0.50
    incorrect
    0.50
    Activations Density 0.000%

    No Known Activations