© 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. 175124
    Prev
    Next
    INDEX
    Explanations

    quality care

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

    organizations, change, packs

    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
    社の
    0.45
    Bibli
    0.44
    
    0.44
    Incoming
    0.43
    サービス
    0.42
    वाँ
    0.42
    টল
    0.41
    🔪
    0.41
    чні
    0.40
    灵活
    0.40
    POSITIVE LOGITS
    খাস্ত
    0.54
    ollow
    0.49
    inds
    0.49
    icron
    0.48
     psyched
    0.48
    anie
    0.47
    inflammation
    0.46
     clamps
    0.46
    ाइंड
    0.46
    awareness
    0.46
    Activations Density 0.002%

    No Known Activations