© 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. 80210
    Prev
    Next
    INDEX
    Explanations

    here / these / if / config file

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

    listed items, specific instructions

    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
    \"
    0.46
    noy
    0.43
    チョ
    0.42
    я
    0.42
    categories
    0.42
    ﺪ
    0.41
    ர்
    0.40
    ₽
    0.39
     bora
    0.39
     /
    0.38
    POSITIVE LOGITS
     hét
    0.51
     lumineux
    0.51
    樯
    0.51
     facteur
    0.50
     derivadas
    0.47
     inspir
    0.47
     nerveux
    0.47
     Physik
    0.47
     presença
    0.47
     Mijn
    0.47
    Activations Density 0.001%

    No Known Activations