© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46302
    Prev
    Next
    INDEX
    Explanations

    beginning actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    に
    0.57
     remain
    0.51
    (
    0.51
     on
    0.50
     masih
    0.50
     telah
    0.49
     sedang
    0.49
     is
    0.48
     była
    0.48
     rasa
    0.48
    POSITIVE LOGITS
     понимать
    0.53
     empiezan
    0.52
     comienzan
    0.51
     Comenz
    0.48
    g
    0.47
     quantified
    0.46
     commencer
    0.46
     Begins
    0.46
    н
    0.46
     verstehen
    0.46
    Activations Density 0.020%

    No Known Activations