© 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. 109525
    Prev
    Next
    INDEX
    Explanations

    programming context or code identifiers

    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
     matemática
    -0.70
    Ȼ
    -0.68
    می
    -0.68
    нансо
    -0.66
     dürfen
    -0.66
     كريم
    -0.65
    為主
    -0.65
    engertian
    -0.65
    ífonos
    -0.65
    豸
    -0.65
    POSITIVE LOGITS
    getParameter
    0.66
     second
    0.65
    HCR
    0.65
     Shat
    0.64
     Raum
    0.63
    zard
    0.63
    Stab
    0.63
    second
    0.63
     bestä
    0.60
    LAX
    0.60
    Activations Density 0.083%

    No Known Activations