© 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. 164892
    Prev
    Next
    INDEX
    Explanations

    is herself

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

    self-care, Porfiry, basis

    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
    מל
    0.53
    לית
    0.48
    匏
    0.47
    াম
    0.47
    idik
    0.47
    নাশ
    0.46
    מית
    0.46
     সঞ্জীবনী
    0.46
     turpentine
    0.45
    פור
    0.44
    POSITIVE LOGITS
    is
    0.58
     تكونوا
    0.49
    immune
    0.45
    queue
    0.44
     v
    0.41
    graphics
    0.41
    coherent
    0.41
    alignment
    0.41
     പിന്നെ
    0.41
    ifstream
    0.40
    Activations Density 0.001%

    No Known Activations