© 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. 10-GEMMASCOPE-RES-131K
    7. 777
    Prev
    Next
    INDEX
    Explanations

    guys

    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_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
    3
    -3.02
    0
    -2.92
    9
    -2.69
    1
    -2.66
    4
    -2.55
    t
    -2.53
    ஂ
    -2.41
    ’
    -2.34
     
    -2.28
    ↵
    -2.23
    POSITIVE LOGITS
    ⸰
    2.80
    providedIn
    2.73
    硨
    2.63
    𖣘
    2.41
    将他
    2.30
     endforeach
    2.20
    埽
    2.14
     />';
    2.11
    operable
    2.11
    })}
    2.11
    Activations Density 0.005%

    No Known Activations