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. 10-GEMMASCOPE-RES-131K
    4. 443
    Prev
    Next
    INDEX
    Explanations

    android dp dimensions

    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_10/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
     and
    -1.80
     it
    -1.79
     or
    -1.51
     системой
    -1.47
     be
    -1.44
    hcm
    -1.44
     exitosa
    -1.36
     оказались
    -1.36
     esquí
    -1.36
     diseñada
    -1.35
    POSITIVE LOGITS
    <bos>
    2.20
    varlak
    1.77
     of
    1.74
    돛
    1.59
    鈑
    1.50
    鐽
    1.43
    zości
    1.41
     enorm
    1.41
     塗装
    1.39
    銥
    1.39
    Activations Density 0.001%

    No Known Activations