© 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. 98658
    Prev
    Next
    INDEX
    Explanations

    trainer status, offering student, countries unreasonably

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

    risk assessment and analysis

    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
    <h4>
    0.57
     orthonormal
    0.56
    銭
    0.54
    <h3>
    0.49
    ニコ
    0.49
    וף
    0.48
    Ա
    0.48
    <h5>
    0.48
    nir
    0.48
     constructors
    0.47
    POSITIVE LOGITS
     precipitated
    0.50
    otive
    0.46
    æss
    0.46
    ilian
    0.46
     ఎలాంటి
    0.45
     Feliz
    0.44
     precipit
    0.44
    ir
    0.44
    isEmpty
    0.44
     Cl
    0.44
    Activations Density 0.000%

    No Known Activations