© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102036
    Prev
    Next
    INDEX
    Explanations

    Cher prefix names or Gerber format

    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
    ).
    -2.64
    ܜ
    -2.63
    哢
    -2.47
     για
    -2.42
    )$
    -2.34
    }$.
    -2.28
    鈊
    -2.23
    嫫
    -2.23
     оценка
    -2.22
    ll
    -2.19
    POSITIVE LOGITS
    ский
    3.19
    where
    2.80
    }
    2.66
    𞤢
    2.42
    ى
    2.39
     lesquelles
    2.38
    ᠂
    2.34
    6
    2.23
    ية
    2.20
    Your
    2.20
    Activations Density 0.001%

    No Known Activations