© 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. 200359
    Prev
    Next
    INDEX
    Explanations

    extended warranty, university towns, wound healing

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

    multilingual greetings or formal phrasing

    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
    Abs
    0.45
    in
    0.43
     hent
    0.42
    -
    0.42
     বর্ণিত
    0.41
    Sin
    0.41
    Note
    0.40
    pekt
    0.40
     variant
    0.39
    ci
    0.39
    POSITIVE LOGITS
    옥
    0.51
     یه
    0.50
    려
    0.50
     arası
    0.49
    ---’
    0.49
     कोविड
    0.49
    ״
    0.49
     വൈദ്യുതി
    0.48
     tố
    0.48
    ﺝ
    0.47
    Activations Density 0.001%

    No Known Activations