© 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. 34-GEMMASCOPE-RES-131K
    7. 62949
    Prev
    Next
    INDEX
    Explanations

    truth be told, be known

    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
    Sciences
    -0.79
    Sting
    -0.76
     τό
    -0.73
    Voyage
    -0.70
     komment
    -0.69
     여
    -0.68
    overs
    -0.68
     profilo
    -0.67
     Calling
    -0.67
     Classi
    -0.67
    POSITIVE LOGITS
     Apel
    0.71
    下げ
    0.69
     mezzanine
    0.68
    罐
    0.65
    vv
    0.65
     requisition
    0.65
     earl
    0.65
    UZ
    0.64
    ่อ
    0.64
     Ull
    0.63
    Activations Density 0.077%

    No Known Activations