© 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. 110581
    Prev
    Next
    INDEX
    Explanations

    ideal and desirable states

    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
    kologi
    -0.88
    quee
    -0.88
     relevante
    -0.88
    olum
    -0.80
    合わない
    -0.79
    hika
    -0.79
    springframework
    -0.79
    peur
    -0.78
    hability
    -0.77
    ésor
    -0.77
    POSITIVE LOGITS
     ideal
    6.06
    理想
    5.09
    ideal
    5.03
     ideally
    5.03
    Ideally
    4.84
     Ideally
    4.78
    Ideal
    4.47
     Ideal
    4.44
     idéal
    4.31
     ideale
    3.80
    Activations Density 0.206%

    No Known Activations