© 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. 109791
    Prev
    Next
    INDEX
    Explanations

    your parents use singing

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

    explaining the next steps

    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
     S
    0.59
     s
    0.59
    s
    0.56
    i
    0.53
     U
    0.50
     Ni
    0.50
     medicina
    0.49
     Chain
    0.49
     D
    0.48
     Bj
    0.47
    POSITIVE LOGITS
    страницу
    0.49
     dirigeants
    0.49
    Buenas
    0.48
    मांड
    0.48
    äne
    0.48
     изначально
    0.48
    μένο
    0.46
     पुढे
    0.46
    ્રા
    0.46
     лінії
    0.45
    Activations Density 0.001%

    No Known Activations