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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26685
    Prev
    Next
    INDEX
    Explanations

    nothing to do with

    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
    鹩
    -1.85
    ᯾
    -1.49
     a
    -1.42
    
    -1.42
    蕓
    -1.38
    ÈS
    -1.35
     freio
    -1.34
    〜〜
    -1.33
    ᕱ
    -1.33
     ajuta
    -1.32
    POSITIVE LOGITS
    it
    1.73
     -
    1.36
     Когда
    1.23
     When
    1.23
    }
    1.21
     whatsoever
    1.20
    p
    1.16
     or
    1.16
    äiv
    1.16
    甚至是
    1.12
    Activations Density 0.009%

    No Known Activations