© 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. 226182
    Prev
    Next
    INDEX
    Explanations

    online customer, without mascara

    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
     Incorpor
    0.46
    Incorpor
    0.44
     incorpora
    0.42
     यूँ
    0.42
    incorporated
    0.40
     входя
    0.40
    );
    0.39
     অন্ত
    0.39
     способность
    0.38
     страте
    0.38
    POSITIVE LOGITS
     annuities
    0.53
     Vuitton
    0.52
     ampere
    0.50
    intestin
    0.49
     a
    0.49
     adware
    0.48
     liquor
    0.48
    副作用
    0.47
     strane
    0.47
     dolls
    0.47
    Activations Density 0.002%

    No Known Activations