© 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. 204418
    Prev
    Next
    INDEX
    Explanations

    general action or state

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

    specifying a style or persona

    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
    ێکی
    0.45
    从事
    0.44
    posição
    0.42
     heiß
    0.42
    】-
    0.42
    pä
    0.41
    ठा
    0.41
     "?"]
    0.41
    ოვანი
    0.41
    锡
    0.41
    POSITIVE LOGITS
     l
    0.52
    μως
    0.49
     pubblic
    0.49
     démontré
    0.46
    াহার
    0.46
    шты
    0.44
     дворе
    0.44
     তবে
    0.44
     però
    0.44
    ঁর
    0.44
    Activations Density 0.000%

    No Known Activations