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. 7693
    Prev
    Next
    INDEX
    Explanations

    in nature

    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
     of
    -1.08
     for
    -1.07
    :……
    -1.03
     which
    -1.00
     or
    -0.98
     from
    -0.98
     betterment
    -0.96
    AHULUAN
    -0.92
     an
    -0.91
     ease
    -0.91
    POSITIVE LOGITS
    compared
    1.27
     dealings
    1.16
    Cevap
    1.13
    despite
    1.07
    suggest
    1.03
    helping
    1.02
     カットソー
    1.02
     dedans
    1.02
     nature
    1.01
     propone
    1.00
    Activations Density 0.090%

    No Known Activations