© 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. 162228
    Prev
    Next
    INDEX
    Explanations

    personal home

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

    specific features

    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
     เนี่ย
    0.45
     けど
    0.43
    ্রিয়া
    0.43
     ქ
    0.42
     buildFor
    0.42
     kulture
    0.42
    husband
    0.41
    デュ
    0.41
    mäßige
    0.41
    Ᏸ
    0.41
    POSITIVE LOGITS
    ل
    0.51
    ار
    0.48
    中午
    0.48
     Start
    0.48
    ص
    0.48
     Still
    0.48
    ivals
    0.47
     Surv
    0.46
    쪽
    0.46
     Sob
    0.46
    Activations Density 0.001%

    No Known Activations