© 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. 89543
    Prev
    Next
    INDEX
    Explanations

    administered dose-dependent liver toxin

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

    describing AI capabilities

    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
     Nh
    0.49
     Bless
    0.48
    Bless
    0.46
     =
    0.46
     Matemat
    0.45
     Ellos
    0.45
     dodat
    0.44
    স্থানের
    0.44
    C
    0.44
    點
    0.44
    POSITIVE LOGITS
     predominant
    0.43
     cytos
    0.43
     bodice
    0.41
     mesenchymal
    0.41
    াইয়৷
    0.41
    quasi
    0.40
    াহিনী
    0.40
    РО
    0.39
    చ్చు
    0.39
    సై
    0.39
    Activations Density 0.002%

    No Known Activations