© 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. 609
    Prev
    Next
    INDEX
    Explanations

    getting along with

    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
    ueltos
    -1.65
    躄
    -1.65
    KommentareTeilen
    -1.63
    atasaray
    -1.60
     ensure
    -1.58
    ⤥
    -1.58
     in
    -1.56
     to
    -1.52
    の人は
    -1.51
    unikasi
    -1.48
    POSITIVE LOGITS
    «.
    1.54
    “,
    1.51
    )
    1.41
    j
    1.41
    «,
    1.39
    “.
    1.35
    とか
    1.34
    LINKS
    1.32
     takiego
    1.32
    \
    1.30
    Activations Density 0.008%

    No Known Activations