© 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. 155574
    Prev
    Next
    INDEX
    Explanations

    every Saturday, week

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

    models (

    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
     renouvel
    0.54
    тропо
    0.49
    戲
    0.48
     fonction
    0.46
     хви
    0.45
    統領
    0.45
    gleichen
    0.45
    ឡ
    0.45
    واز
    0.44
    Atlet
    0.44
    POSITIVE LOGITS
    inition
    0.47
     রাজ্যের
    0.46
    ay
    0.45
    EntityType
    0.45
    💴
    0.44
    ic
    0.44
    🅴
    0.44
    ﺔ
    0.44
    £
    0.43
    órmula
    0.42
    Activations Density 0.000%

    No Known Activations