© 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. 198458
    Prev
    Next
    INDEX
    Explanations

    phrase followed by specific word

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

    storytelling, getting rid

    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
    ীব্র
    0.48
    getValue
    0.47
    值的
    0.45
    এর
    0.44
    Φ
    0.43
    VALUES
    0.42
    蔬
    0.42
    后续
    0.42
     onPressed
    0.42
    اث
    0.42
    POSITIVE LOGITS
     inhabiting
    0.45
     Stol
    0.44
     Bukh
    0.43
     Avila
    0.42
     மொ
    0.42
     approx
    0.41
     Wilk
    0.41
     eki
    0.41
    kontakt
    0.41
     Isis
    0.41
    Activations Density 0.000%

    No Known Activations