© 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. 48342
    Prev
    Next
    INDEX
    Explanations

    followed by conditions or reasons

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

    creating movie scripts

    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
    大部分
    0.52
    ك
    0.52
    خته
    0.50
     Vorstand
    0.50
    ચી
    0.49
     آئی
    0.48
    职工
    0.48
    东
    0.47
    ayeva
    0.47
    ра
    0.47
    POSITIVE LOGITS
     nutty
    0.49
    protein
    0.46
     adaptability
    0.45
     malicious
    0.44
     наста
    0.44
     protein
    0.44
    ЛЕ
    0.43
     inexplicable
    0.43
     onslaught
    0.42
    letic
    0.41
    Activations Density 0.000%

    No Known Activations