© 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. 83450
    Prev
    Next
    INDEX
    Explanations

    worry about, should be, foil tapes

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

    work package leads

    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
     अंकित
    0.56
     Elinor
    0.54
    devtools
    0.49
     inpatient
    0.48
     europea
    0.48
     連
    0.47
     odv
    0.47
     耳
    0.47
     Anu
    0.46
    iatica
    0.46
    POSITIVE LOGITS
    0
    0.50
    ц
    0.45
    ар
    0.44
    يرة
    0.44
    و
    0.44
     وش
    0.44
    𝟎
    0.43
    اة
    0.42
    ாரா
    0.42
    г
    0.42
    Activations Density 0.000%

    No Known Activations