© 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. 145968
    Prev
    Next
    INDEX
    Explanations

    orbit around

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

    tokens vs words

    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
    про
    0.52
    瞽
    0.50
    प्या
    0.49
    राष्ट्रपति
    0.49
    פ
    0.49
     числі
    0.49
    א
    0.49
    缡
    0.48
    приклад
    0.48
    ઓ
    0.48
    POSITIVE LOGITS
     suburbs
    0.52
     sites
    0.51
     optimizations
    0.47
     bulletins
    0.46
     lattice
    0.46
    ."""
    0.46
     frees
    0.46
     solver
    0.46
     variants
    0.45
     geometries
    0.45
    Activations Density 0.001%

    No Known Activations