© 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. 251102
    Prev
    Next
    INDEX
    Explanations

    names of politicians and related events

    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
    ala
    0.47
     Vans
    0.45
    드
    0.44
    トレー
    0.44
    か
    0.43
    échange
    0.42
    躓
    0.42
    کے
    0.41
    先輩
    0.41
    APAN
    0.41
    POSITIVE LOGITS
     mikä
    0.47
     contributions
    0.46
     konci
    0.43
     muncul
    0.43
     contrib
    0.40
     caller
    0.40
     efeitos
    0.40
     effects
    0.39
     patched
    0.39
     появление
    0.39
    Activations Density 0.000%

    No Known Activations