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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13796
    Prev
    Next
    INDEX
    Explanations

    names and morpholine

    np_acts-logits-general · gemini-2.5-flash-lite

    names and words with capitalized first letters, particularly people's names.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    on
    -2.80
    ஂ
    -2.56
    this
    -2.53
    型的
    -2.45
    al
    -2.39
    宬
    -2.38
    l
    -2.33
    榦
    -2.33
    蔸
    -2.31
    i
    -2.25
    POSITIVE LOGITS
    ፨
    2.30
    梱
    2.22
     defunct
    2.22
    言语
    2.20
    弐
    2.17
    What
    2.13
     şun
    2.11
     spécialisé
    2.11
    皺
    2.11
     demoral
    2.09
    Activations Density 0.008%

    No Known Activations