© 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. 177781
    Prev
    Next
    INDEX
    Explanations

    all other, next stop, depending on

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

    negative or technical descriptions

    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
     പ്രവര്‍ത്തന
    0.55
     이하
    0.54
     졸업
    0.52
     높은
    0.50
     장애
    0.50
     lèvres
    0.49
    日記
    0.49
     :+:
    0.48
    نٹ
    0.48
     ഓര്‍
    0.48
    POSITIVE LOGITS
    y
    0.52
    u
    0.47
    ками
    0.46
    Indigenous
    0.44
    Form
    0.43
    )
    0.42
    Mut
    0.42
    s
    0.41
    Full
    0.41
     Ques
    0.40
    Activations Density 0.000%

    No Known Activations