© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11516
    Prev
    Next
    INDEX
    Explanations

    investigation and resignation announcements

    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
    !
    -1.20
     diferenças
    -1.20
    ׇ
    -1.19
     چربی
    -1.15
    COMPAR
    -1.10
     congested
    -1.08
    ױ
    -1.04
     förslag
    -1.00
     тонн
    -0.99
     mesmas
    -0.99
    POSITIVE LOGITS
     employees
    1.42
     investigation
    1.39
     employee
    1.24
    ᾿
    1.22
     administrative
    1.20
    ַּ
    1.18
    וּ
    1.17
    ּוֹ
    1.17
     ethical
    1.16
     procedural
    1.14
    Activations Density 0.048%

    No Known Activations