© 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. 33312
    Prev
    Next
    INDEX
    Explanations

    HTML style attribute

    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
     any
    -1.34
    
    -1.31
    与此同时
    -1.30
    がありますが
    -1.25
     other
    -1.24
    などが
    -1.24
    齟
    -1.23
     those
    -1.20
    ftrag
    -1.20
     Songtext
    -1.16
    POSITIVE LOGITS
    ⒉
    1.41
     hermosos
    1.31
     estadounidenses
    1.27
    rédients
    1.27
     coger
    1.24
     nef
    1.23
     برنامج
    1.21
    –
    1.21
    öße
    1.20
     alimenti
    1.20
    Activations Density 0.002%

    No Known Activations