© 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. 141617
    Prev
    Next
    INDEX
    Explanations

    Team and collaborative actions

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

    types of technical terms

    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
    5
    0.63
    3
    0.59
    f
    0.59
    4
    0.59
    9
    0.56
    auk
    0.54
    ud
    0.54
    ef
    0.54
    ai
    0.53
    flex
    0.51
    POSITIVE LOGITS
     مشترك
    0.57
    交换
    0.46
    球队
    0.46
     atlet
    0.46
    ーター
    0.46
     imposs
    0.45
     대체
    0.45
    实话
    0.45
    岷
    0.45
    协作
    0.44
    Activations Density 0.002%

    No Known Activations