© 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. 11459
    Prev
    Next
    INDEX
    Explanations

    location descriptions

    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
    </sup>
    -1.20
    είτε
    -1.09
    рующие
    -1.09
    艹
    -1.09
     Beispiel
    -1.07
    </h2>
    -1.07
     finca
    -1.02
    âh
    -1.02
    已经
    -1.02
    ponible
    -1.02
    POSITIVE LOGITS
    各有
    1.22
     abends
    1.22
     albeit
    1.21
     carreaux
    1.19
    かったです
    1.18
    ījum
    1.16
     кото
    1.14
    nhung
    1.14
    pentru
    1.13
    (":
    1.12
    Activations Density 0.004%

    No Known Activations