© 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. 29088
    Prev
    Next
    INDEX
    Explanations

    positive descriptions

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

    maintained

    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
     хотелось
    0.44
    栢
    0.42
    ское
    0.41
    斯
    0.40
    Surely
    0.40
    맏
    0.40
    Deutschland
    0.40
    창
    0.40
    における
    0.39
    <0xE9>
    0.39
    POSITIVE LOGITS
     undamaged
    0.46
     alumna
    0.46
     Nt
    0.44
     because
    0.42
     trimester
    0.41
     !!!!
    0.41
     nt
    0.41
     impairments
    0.40
     seulement
    0.40
     freshmen
    0.40
    Activations Density 0.000%

    No Known Activations