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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110613
    Prev
    Next
    INDEX
    Explanations

    please, if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    :
    -1.21
     redan
    -1.14
    +");
    -1.12
    vidos
    -1.08
     consultato
    -1.08
    ᵒ
    -1.04
    [>
    -1.03
    ⇐
    -1.03
    lleri
    -1.02
    ":{
    -1.01
    POSITIVE LOGITS
     please
    3.03
     you
    2.75
    Please
    2.53
     if
    2.39
     Please
    2.27
     your
    2.06
     all
    2.06
     we
    1.91
     there
    1.77
     PLEASE
    1.73
    Activations Density 0.077%

    No Known Activations