© 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. 10-GEMMASCOPE-RES-131K
    7. 59119
    Prev
    Next
    INDEX
    Explanations

    interesting information

    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
    を
    -1.59
     a
    -1.48
    是
    -1.45
    ጺ
    -1.43
    十分
    -1.38
    以上
    -1.38
     scoperto
    -1.38
     créées
    -1.36
     furia
    -1.33
    ati
    -1.32
    POSITIVE LOGITS
     but
    2.47
     interesting
    1.61
     also
    1.60
     nhưng
    1.49
    贔
    1.48
     if
    1.47
    却又
    1.41
     umožňuje
    1.39
     empez
    1.38
     although
    1.36
    Activations Density 0.040%

    No Known Activations