© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11938
    Prev
    Next
    INDEX
    Explanations

    conditional statements and applications

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

    the word "Conditional" at the beginning of titles, class names, or technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𞤤
    -2.83
     ogrom
    -2.61
    pecabe
    -2.58
    viele
    -2.55
    archiwizowane
    -2.55
    纐
    -2.47
    ⧠
    -2.41
     astonishing
    -2.36
    嘥
    -2.33
     his
    -2.28
    POSITIVE LOGITS
    When
    3.34
    It
    3.33
    After
    3.27
    While
    3.23
    The
    3.23
    6
    3.03
    1
    3.02
    This
    3.02
    If
    3.00
    Because
    2.98
    Activations Density 0.006%

    No Known Activations