© 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. 34-GEMMASCOPE-RES-131K
    7. 117900
    Prev
    Next
    INDEX
    Explanations

    State Police, Summer Heat

    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_34/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
    –
    -1.28
    C
    -1.15
    …
    -1.10
    H
    -1.07
    I
    -1.06
     großartige
    -1.05
     einzigartige
    -1.01
     tivesse
    -1.01
     schnelle
    -1.01
    nový
    -1.00
    POSITIVE LOGITS
     plafon
    1.22
    ?」
    1.17
     graphiques
    1.17
     boste
    1.17
     اصلی
    1.17
     cérami
    1.16
     Ă
    1.14
     INCLUD
    1.14
    STALK
    1.12
    、「
    1.10
    Activations Density 0.017%

    No Known Activations