© 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. 178017
    Prev
    Next
    INDEX
    Explanations

    mechanisms, dropping, regularly, Dim, competition, revolver

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

    questions and harmful content

    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
    新鲜
    0.53
     avión
    0.49
    现在
    0.49
    不超过
    0.47
    勮
    0.47
     electrónicos
    0.47
     rápida
    0.46
     rápidos
    0.46
    надцати
    0.44
    вети
    0.44
    POSITIVE LOGITS
     wrongdoing
    0.46
    the
    0.46
     discomfort
    0.46
     undue
    0.46
    his
    0.45
    Ibid
    0.45
     derogatory
    0.44
     logement
    0.43
     soundness
    0.43
    쉰
    0.43
    Activations Density 0.001%

    No Known Activations