© 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. 28669
    Prev
    Next
    INDEX
    Explanations

    wiring diagram symbols

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

    discourage use of certain things

    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
    headline
    0.44
    gradle
    0.43
     धूमधाम
    0.43
    classified
    0.42
    󠁢
    0.42
     তুমি
    0.42
     ನನ್ನ
    0.41
     एमएन
    0.41
    〢
    0.41
    entrée
    0.41
    POSITIVE LOGITS
     disamb
    0.48
     intuitive
    0.46
     inadvert
    0.45
     permissive
    0.44
     confl
    0.44
    越来越
    0.43
     avoids
    0.43
     senare
    0.43
     differentiating
    0.43
     zunehm
    0.43
    Activations Density 0.001%

    No Known Activations