© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16374
    Prev
    Next
    INDEX
    Explanations

    DOS velocity ResourceId schedule

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

    conditional logic and comparisons

    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_16k_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
    flox
    0.41
    lof
    0.40
    gr
    0.40
     ク
    0.37
    neath
    0.37
    copic
    0.37
    definition
    0.36
     ())
    0.36
     ቁ
    0.36
    brug
    0.35
    POSITIVE LOGITS
     hacía
    0.40
    утбу
    0.39
     şidd
    0.39
     găsit
    0.39
     debía
    0.38
    ólogo
    0.38
    شرات
    0.38
    ESCAPE
    0.38
     yanlış
    0.38
     quién
    0.38
    Activations Density 0.001%

    No Known Activations