© 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. 22-GEMMASCOPE-RES-131K
    7. 11299
    Prev
    Next
    INDEX
    Explanations

    code delimiters and comments

    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
     because
    -1.19
     became
    -1.09
     old
    -1.09
     gave
    -1.08
     which
    -1.08
    زيل
    -1.07
     first
    -1.06
    ⸼
    -1.06
     took
    -1.05
     before
    -1.04
    POSITIVE LOGITS
     grecque
    1.17
    </i>
    1.17
     '-
    1.15
    ',
    1.14
    ‗
    1.13
    בוק
    1.13
     也
    1.12
    通常
    1.10
     unsettling
    1.10
     ſtate
    1.09
    Activations Density 0.004%

    No Known Activations