© 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. 217150
    Prev
    Next
    INDEX
    Explanations

    supports Debian

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

    different sectors have different dynamics

    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
    inst
    0.46
    Michael
    0.46
    <0xBC>
    0.45
    Warn
    0.44
    Hint
    0.43
    Tint
    0.42
    il
    0.41
    ঃ
    0.41
    №
    0.41
    Hz
    0.41
    POSITIVE LOGITS
     aggior
    0.55
     déta
    0.52
     supermerc
    0.52
     trover
    0.50
     vendedor
    0.50
     deben
    0.49
     prévu
    0.49
     edilir
    0.49
     punti
    0.47
     lütfen
    0.47
    Activations Density 0.001%

    No Known Activations