© 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. 128675
    Prev
    Next
    INDEX
    Explanations

    significance statement or question followed by an answer

    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
    ća
    -0.84
     any
    -0.81
     Okan
    -0.81
    同伴
    -0.79
    แล้ว
    -0.76
     never
    -0.76
     Hvad
    -0.75
     Gibt
    -0.75
    Jäh
    -0.75
     Tasmania
    -0.75
    POSITIVE LOGITS
     رمضان
    0.98
    vamo
    0.94
     pesa
    0.94
    getOne
    0.90
    terno
    0.88
     fevere
    0.88
    Puppy
    0.88
    nation
    0.86
    ENTY
    0.85
    gehend
    0.84
    Activations Density 0.002%

    No Known Activations