© 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. 224588
    Prev
    Next
    INDEX
    Explanations

    conversational continuations

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

    word segments and following words

    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
    Ꮔ
    0.57
    руса
    0.50
    リック
    0.50
     fistule
    0.49
    стойчи
    0.48
     термин
    0.48
    Ꮞ
    0.48
    禎
    0.47
     সুদর্শন
    0.46
     tenacity
    0.46
    POSITIVE LOGITS
    aba
    0.52
     s
    0.52
    ett
    0.45
    igu
    0.45
     Seu
    0.45
     Tudo
    0.44
     l
    0.44
    ’,
    0.42
    ondo
    0.42
     khô
    0.42
    Activations Density 0.001%

    No Known Activations