Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11757
    Prev
    Next
    INDEX
    Explanations

    confirming or ensuring outcomes

    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_22/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
     Тогда
    -1.18
    Angebot
    -1.09
    pertory
    -1.09
     stormy
    -1.05
     attesa
    -1.03
    Sekarang
    -1.03
    ’,
    -1.01
    őben
    -0.98
    hány
    -0.98
    🖲
    -0.98
    POSITIVE LOGITS
    不会
    1.01
     wasn
    1.01
    joyed
    0.99
     plenty
    0.98
    ensure
    0.98
     isn
    0.97
     NOT
    0.96
    Shouldn
    0.96
    cisive
    0.96
    understood
    0.95
    Activations Density 0.036%

    No Known Activations