© 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-16K
    7. 2483
    Prev
    Next
    INDEX
    Explanations

    variable outcomes

    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_16k_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
     iemand
    0.36
    នូវ
    0.35
    :
    0.35
     JUST
    0.35
     instead
    0.34
    నుక
    0.34
     нен
    0.34
     বিগত
    0.33
     somewhere
    0.33
     যখন
    0.33
    POSITIVE LOGITS
    obviously
    0.51
     dependiendo
    0.49
     ד
    0.48
    ák
    0.46
    depending
    0.46
     varies
    0.46
     různ
    0.46
    owano
    0.45
     tergantung
    0.45
     según
    0.43
    Activations Density 0.338%

    No Known Activations