© 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. 106164
    Prev
    Next
    INDEX
    Explanations

    entering or exiting places

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

    walk into difficult situations

    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
    ح
    0.75
    it
    0.68
    kę
    0.67
    ką
    0.65
    ai
    0.64
    기
    0.64
    .
    0.59
    （
    0.59
    ᵕ
    0.58
    kut
    0.56
    POSITIVE LOGITS
     brazen
    0.72
    н
    0.61
     ricev
    0.57
     receb
    0.56
    т
    0.55
     поддержки
    0.55
     casado
    0.55
     firmado
    0.54
    ди
    0.54
    น
    0.54
    Activations Density 0.068%

    No Known Activations