© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 47807
    Prev
    Next
    INDEX
    Explanations

    conditional statements or comparisons

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

    trendy restaurant

    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
     genotyping
    0.46
     CAMP
    0.45
     saucer
    0.45
     décor
    0.44
     CDR
    0.44
     testimonials
    0.44
    l
    0.43
     templates
    0.43
    tp
    0.43
     Système
    0.42
    POSITIVE LOGITS
    }-\
    0.45
    }=-\
    0.45
     如果
    0.45
     বৃহত্তর
    0.45
    اگر
    0.44
     apabila
    0.44
     Bahkan
    0.44
     महान
    0.44
     निय
    0.44
     đòi
    0.44
    Activations Density 0.000%

    No Known Activations