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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110303
    Prev
    Next
    INDEX
    Explanations

    specific value or level

    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
    respectively
    -1.18
     garantías
    -1.13
    kinda
    -1.13
    entitled
    -1.12
     personagens
    -1.12
     totalement
    -1.06
     pomoci
    -1.06
    kinds
    -1.05
     ་
    -1.05
     APPELLANT
    -1.05
    POSITIVE LOGITS
     value
    1.84
     figure
    1.42
     level
    1.42
     for
    1.27
     amount
    1.23
     because
    1.18
     after
    1.13
    值
    1.11
     requirement
    1.09
     while
    1.09
    Activations Density 0.135%

    No Known Activations