© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14058
    Prev
    Next
    INDEX
    Explanations

    pub followed by / or med

    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
    </h3>
    -3.00
     —
    -2.72
    轳
    -2.33
    谞
    -2.31
     are
    -2.23
     dejo
    -2.23
     pido
    -2.17
    ICOLON
    -2.08
    潆
    -2.03
    糅
    -1.99
    POSITIVE LOGITS
    Ironically
    2.64
    a
    2.47
     rajut
    2.44
    </b>
    2.44
    蹓
    2.38
    從
    2.36
     parteci
    2.30
     makinesi
    2.28
    hline
    2.27
    }$
    2.25
    Activations Density 0.004%

    No Known Activations