© 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. 15720
    Prev
    Next
    INDEX
    Explanations

    sub

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

    special characters followed by identifiers

    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
    ↵
    0.43
    _
    0.42
    S
    0.41
    M
    0.40
     I
    0.38
     T
    0.38
     />
    0.37
     G
    0.37
     Data
    0.37
     使用
    0.37
    POSITIVE LOGITS
    UILLER
    0.40
     polypes
    0.37
     rameaux
    0.37
     spermatozoa
    0.37
     invertebr
    0.35
     sillons
    0.35
     austenitic
    0.35
    Gosudarstvennyj
    0.35
     humus
    0.35
     glandes
    0.35
    Activations Density 0.011%

    No Known Activations