© 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. 57530
    Prev
    Next
    INDEX
    Explanations

    criticism from other sources

    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
    hány
    -1.48
    nargs
    -1.35
    diki
    -1.26
    
    -1.20
    providedIn
    -1.20
    ǁ
    -1.19
     jego
    -1.18
     gonna
    -1.17
    ᅠ
    -1.17
    geq
    -1.16
    POSITIVE LOGITS
     from
    2.22
     by
    2.17
    同样的
    1.23
     Kartoffeln
    1.23
    可能的
    1.17
     there
    1.15
    這就是
    1.13
     può
    1.13
    embolso
    1.13
     vanuit
    1.12
    Activations Density 0.080%

    No Known Activations