© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 668
    Prev
    Next
    INDEX
    Explanations

    names ending in ood, och, ost, oy, osa, olo, ox, od, homa

    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
    what
    -2.67
    ⵌ
    -2.47
    there
    -2.47
    just
    -2.42
     hermosas
    -2.36
     After
    -2.34
    section
    -2.33
     sonriendo
    -2.31
     號
    -2.30
     berkualitas
    -2.28
    POSITIVE LOGITS
    渼
    3.23
     exceedingly
    2.64
    ↵
    2.59
    櫪
    2.58
    厹
    2.56
     languid
    2.56
     of
    2.56
    你和
    2.53
     tetapi
    2.48
    ৢ
    2.48
    Activations Density 3.052%

    No Known Activations