© 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. 17039
    Prev
    Next
    INDEX
    Explanations

    this [entity]

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

    this place is

    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
    谕
    0.50
     podamos
    0.48
     svih
    0.48
     mengen
    0.47
     dalších
    0.46
     menú
    0.46
     сегодняшний
    0.46
     evolução
    0.45
     cena
    0.45
     sämt
    0.45
    POSITIVE LOGITS
    ט
    0.46
    ชค
    0.45
    adjacent
    0.45
    Microsoft
    0.44
     розташо
    0.42
    ayette
    0.42
    տն
    0.42
    DummyView
    0.41
    farming
    0.40
    Соцмережа
    0.40
    Activations Density 0.010%

    No Known Activations