© 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. 12377
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     from
    -1.40
    ︱
    -1.13
    ＝＝＝＝
    -1.12
    不斷
    -1.10
     RECOMM
    -1.10
     keperluan
    -1.09
     ucapan
    -1.08
    壜
    -1.06
    今度
    -1.05
    が無い
    -1.04
    POSITIVE LOGITS
    /
    1.27
    $
    1.27
    '
    1.25
    \
    1.20
    *
    1.17
    ]
    1.16
    "
    1.16
    )
    1.15
    j
    1.15
    gn
    1.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.