© 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. 190697
    Prev
    Next
    INDEX
    Explanations

    of course

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

    compartment

    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
    ීමට
    0.46
    ప్రదేశ్
    0.45
    astype
    0.45
    нету
    0.45
    Ѳ
    0.45
    واقع
    0.43
     окружающей
    0.43
    əsi
    0.42
    धनों
    0.42
    phonon
    0.42
    POSITIVE LOGITS
     terminer
    0.48
    すると
    0.45
    다
    0.45
    น้อง
    0.44
     fabricante
    0.44
    反映
    0.43
     Cap
    0.43
     Franz
    0.42
     Deux
    0.42
     Locke
    0.42
    Activations Density 0.000%

    No Known Activations