© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99745
    Prev
    Next
    INDEX
    Explanations

    occupation, location, or state

    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
     Inſ
    -1.30
     انسانی
    -1.28
    キーボード
    -1.27
     kampus
    -1.27
     haja
    -1.27
     miſ
    -1.24
    皈
    -1.24
     ſp
    -1.23
     alip
    -1.22
     kado
    -1.22
    POSITIVE LOGITS
     or
    1.31
     had
    1.31
     markedly
    1.30
     descrito
    1.30
    rašymas
    1.25
     their
    1.25
     during
    1.23
     overtly
    1.23
     decreased
    1.19
     presumably
    1.17
    Activations Density 0.863%

    No Known Activations