© 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. 37099
    Prev
    Next
    INDEX
    Explanations

    world war ii events and entities

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

    invasion of Poland 1939

    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
     ১৯৬
    0.48
     ১৯৭
    0.46
     মহাশয়
    0.46
     codimension
    0.46
     objectMapper
    0.43
     ቲ
    0.42
     ১৯৬৫
    0.40
    嘉
    0.39
    ບບ
    0.39
     ৭৫
    0.38
    POSITIVE LOGITS
    gment
    0.48
     Quarantine
    0.46
     напа
    0.46
     enviado
    0.45
     خفیہ
    0.43
    निर्भर
    0.43
     Teng
    0.43
     lente
    0.43
     Axis
    0.41
     attacked
    0.41
    Activations Density 0.047%

    No Known Activations