© 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. 233175
    Prev
    Next
    INDEX
    Explanations

    business, awards, news, awards, information

    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
    वरणीय
    0.57
     teaching
    0.49
     therapy
    0.47
     harmonics
    0.47
     buddhist
    0.46
     klinik
    0.45
    拈
    0.45
     reachable
    0.45
     chants
    0.44
     daran
    0.44
    POSITIVE LOGITS
    Stabil
    0.52
     Stabil
    0.47
     своего
    0.45
    Buyer
    0.43
     стабили
    0.42
    spo
    0.42
    자로
    0.42
    석
    0.41
     Kunde
    0.41
     GARC
    0.40
    Activations Density 0.001%

    No Known Activations