© 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. 105857
    Prev
    Next
    INDEX
    Explanations

    October October's October

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

    analyzing and structuring information

    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
     hypers
    0.43
    엥
    0.41
    Graf
    0.39
    であることが
    0.39
    proportion
    0.39
    В
    0.38
     gusts
    0.38
     fluency
    0.38
    Е
    0.38
    女性
    0.37
    POSITIVE LOGITS
     сегодняшний
    0.49
    🫶
    0.46
     ❤️
    0.45
     aceste
    0.45
     ajutor
    0.45
     posao
    0.45
     deseja
    0.45
    ❤️❤️
    0.45
     octombrie
    0.45
     legado
    0.45
    Activations Density 0.004%

    No Known Activations