© 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. 24462
    Prev
    Next
    INDEX
    Explanations

    date, number, and quantity

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

    feelings and states

    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
     incorporar
    0.46
     avulla
    0.46
    铷
    0.44
     দ্বারা
    0.42
     OPT
    0.41
     WITH
    0.41
     প্রত্যেক
    0.41
     গ্রন্থে
    0.40
     लगाकर
    0.40
     کارڈ
    0.40
    POSITIVE LOGITS
    この記事
    0.47
    Ids
    0.41
    旌
    0.41
    РИ
    0.41
    yzed
    0.40
    colnames
    0.40
    ítése
    0.40
    nivel
    0.38
    స్తున్న
    0.38
    appendix
    0.38
    Activations Density 0.010%

    No Known Activations