© 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. 73983
    Prev
    Next
    INDEX
    Explanations

    list management

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

    individual assets, investments

    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
     \|\
    0.55
    stethoscope
    0.49
     Staples
    0.49
     "+"
    0.49
    lub
    0.49
    ücken
    0.48
    uv
    0.48
    wool
    0.48
    w
    0.48
    ти
    0.48
    POSITIVE LOGITS
    슨
    0.46
    Disney
    0.44
    迪士尼
    0.43
     daughter
    0.42
    แ
    0.42
    OVER
    0.42
    برا
    0.41
    Angry
    0.41
    كتر
    0.41
    他にも
    0.40
    Activations Density 0.000%

    No Known Activations