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. 22-GEMMASCOPE-RES-131K
    4. 11666
    Prev
    Next
    INDEX
    Explanations

    owner suggesting

    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_22/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
    ύ
    -1.17
    mayr
    -1.12
    centiles
    -1.11
    LAUGHTER
    -1.10
    ּוֹ
    -1.07
     خریدار
    -1.06
    ⅽ
    -1.05
    ૩
    -1.05
    formable
    -1.05
     ventajas
    -1.05
    POSITIVE LOGITS
     himself
    1.30
     ouverture
    1.15
     النبات
    1.13
    ocuk
    1.12
     approche
    1.05
    сколько
    1.05
    ׇ
    1.04
    也非常
    1.03
    ycznie
    1.02
    经营
    1.01
    Activations Density 0.010%

    No Known Activations