© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42419
    Prev
    Next
    INDEX
    Explanations

    National Geographic, channels, visual

    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
    I
    -2.59
     یا
    -2.09
    2
    -2.06
    หรือ
    -2.02
    or
    -1.91
    (
    -1.83
    en
    -1.80
    i
    -1.79
    has
    -1.76
    躄
    -1.76
    POSITIVE LOGITS
    ↵
    2.13
    quisar
    1.98
    ”،
    1.94
    jaqueta
    1.94
    彞
    1.89
    鳏
    1.87
    鈐
    1.87
    蝰
    1.84
    咵
    1.84
    pulseira
    1.82
    Activations Density 0.004%

    No Known Activations