© 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. 11027
    Prev
    Next
    INDEX
    Explanations

    input fields and text boxes

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

    form input fields

    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
    EMAN
    0.54
    NEUTRON
    0.54
     embolism
    0.53
    戦闘
    0.52
    Anderson
    0.52
     دری
    0.52
    HEMAT
    0.51
    ⴽ
    0.51
    ೃಷ್ಣ
    0.51
     moléculas
    0.50
    POSITIVE LOGITS
     textarea
    1.02
     Input
    0.99
     input
    0.93
     TextInput
    0.88
    Input
    0.83
    input
    0.82
     输入
    0.82
     TextFormField
    0.82
     TextBox
    0.81
    textarea
    0.81
    Activations Density 0.023%

    No Known Activations