© 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. 111842
    Prev
    Next
    INDEX
    Explanations

    invited Paul Metcalfe

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

    logical fallacy, vegetarian, dormancy, oxide

    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
    ದ್ದರಿಂದ
    0.51
    μων
    0.50
    靣
    0.48
    рили
    0.47
     எதிரான
    0.46
    드로
    0.46
    쪼
    0.46
    querda
    0.44
    舧
    0.44
     예배
    0.44
    POSITIVE LOGITS
     radius
    0.48
     reply
    0.48
     q
    0.48
     scala
    0.47
     odorless
    0.46
     prot
    0.46
     kr
    0.46
     warm
    0.46
     nb
    0.46
     opt
    0.45
    Activations Density 0.001%

    No Known Activations