© 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. 60781
    Prev
    Next
    INDEX
    Explanations

    improving

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

    Abstract Base Classes

    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
     facets
    0.47
     instanceof
    0.46
     adv
    0.45
     faceted
    0.45
     *);
    0.44
     Actress
    0.44
     elusive
    0.43
    yl
    0.42
     subsurface
    0.42
     empowers
    0.42
    POSITIVE LOGITS
     Nos
    0.51
     robbing
    0.50
    регистри
    0.49
    бора
    0.48
    갓
    0.47
     phare
    0.46
    訢
    0.46
    Nos
    0.46
     lorry
    0.46
    AVOA
    0.45
    Activations Density 0.000%

    No Known Activations