© 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. 76384
    Prev
    Next
    INDEX
    Explanations

    input and its context

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

    input refers to data or question

    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
    스
    0.91
    える
    0.81
    ྥ
    0.81
    ود
    0.78
    在
    0.77
    רו
    0.76
    بد
    0.75
    о
    0.75
    ও
    0.74
    ۲
    0.74
    POSITIVE LOGITS
    1
    1.07
     Input
    1.00
    it
    0.98
    as
    0.95
    a
    0.95
     input
    0.89
     Inputs
    0.89
    3
    0.89
    ten
    0.88
    pped
    0.88
    Activations Density 0.016%

    No Known Activations