© 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. 224807
    Prev
    Next
    INDEX
    Explanations

    places, Airport, sentence, River

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

    android:icon

    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
    徽
    0.52
    3
    0.49
    者に
    0.48
    цию
    0.47
    つ
    0.47
    了承
    0.46
    ндай
    0.46
    ¯</
    0.46
     iframe
    0.45
    的的
    0.45
    POSITIVE LOGITS
     universality
    0.49
     transposed
    0.47
     cannabinoids
    0.46
     peptides
    0.44
     ambiguities
    0.44
     morphological
    0.44
     defens
    0.44
     estadísticas
    0.44
     mysteries
    0.44
     neutrinos
    0.43
    Activations Density 0.000%

    No Known Activations