© 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. 28787
    Prev
    Next
    INDEX
    Explanations

    skills, engineer, experience, error

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

    skepticism/doubt

    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
    N
    0.59
    f
    0.55
    imod
    0.52
    F
    0.49
    {(
    0.48
     Genel
    0.46
     الته
    0.46
    x
    0.46
    fire
    0.46
     સો
    0.45
    POSITIVE LOGITS
    یه
    0.49
     অনিশ্চ
    0.47
    শ্যক
    0.45
    Ꮟ
    0.44
     থেকেও
    0.44
     semaines
    0.43
     alemán
    0.43
     পাকিস্তানীরা
    0.42
    ாளையம்
    0.42
     مە
    0.42
    Activations Density 0.000%

    No Known Activations