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. 34-GEMMASCOPE-RES-131K
    4. 8716
    Prev
    Next
    INDEX
    Explanations

    names starting with Ay, Aj, Ae, Ah

    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
    を
    -0.95
    Populations
    -0.90
    途中で
    -0.90
    Quoting
    -0.88
     is
    -0.88
    Veter
    -0.87
    結果は
    -0.86
    commodation
    -0.86
    Harmful
    -0.86
    verages
    -0.85
    POSITIVE LOGITS
    無論
    1.05
    えっ
    1.02
    (^_^
    1.02
    あー
    1.01
    いえ
    0.98
     nadzie
    0.98
    offsetX
    0.95
    usza
    0.93
    あぁ
    0.92
    틀
    0.92
    Activations Density 0.043%

    No Known Activations