© 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. 16365
    Prev
    Next
    INDEX
    Explanations

    booking hotel or car hire

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

    code examples

    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
    ђено
    0.54
    见
    0.51
    אַר
    0.50
    ἅ
    0.50
    Ἁ
    0.50
     gön
    0.49
    锏
    0.48
    डर
    0.47
    𝙘
    0.47
    अप्र
    0.46
    POSITIVE LOGITS
     misplaced
    0.44
     "<
    0.43
    umpy
    0.41
    ?»
    0.41
     ?
    0.41
    ethe
    0.41
    ate
    0.41
     говоря
    0.41
     reportedly
    0.40
     SPEAK
    0.40
    Activations Density 0.001%

    No Known Activations