© 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. 128112
    Prev
    Next
    INDEX
    Explanations

    audit, update, definition, procedure

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

    eczema/dermatitis

    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
    ését
    0.50
    きっと
    0.49
    碛
    0.49
    cznym
    0.46
     مبلغ
    0.45
     علاوه
    0.45
     եւ
    0.45
    كة
    0.44
    czny
    0.44
     кафе
    0.44
    POSITIVE LOGITS
     agriculture
    0.50
     Defined
    0.48
     例
    0.47
     merchandise
    0.44
     ag
    0.43
     epidemiology
    0.43
     EDA
    0.43
                           
    0.43
     rump
    0.42
     Proced
    0.42
    Activations Density 0.000%

    No Known Activations