© 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. 41712
    Prev
    Next
    INDEX
    Explanations

    stand out, through difficult

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

    jokes and instructions

    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
    s
    0.62
    nes
    0.52
    у
    0.49
     this
    0.49
    nasa
    0.49
     integro
    0.48
    r
    0.48
    ru
    0.47
    lø
    0.46
    при
    0.46
    POSITIVE LOGITS
     نسبت
    0.52
     exclusivamente
    0.46
     λοι
    0.44
     χωρίς
    0.44
     necesariamente
    0.44
     έως
    0.43
     পুত্র
    0.42
    ätten
    0.42
    に対して
    0.42
    座椅
    0.41
    Activations Density 0.000%

    No Known Activations