© 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. 22-GEMMASCOPE-RES-131K
    7. 35430
    Prev
    Next
    INDEX
    Explanations

    names followed by punctuation

    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
     and
    -1.59
     klachten
    -1.15
    際に
    -1.15
     offering
    -1.10
    ことも
    -1.05
    ことは
    -1.02
     at
    -1.02
    ところに
    -1.02
     there
    -1.01
     inoltre
    -1.01
    POSITIVE LOGITS
    ですが
    1.25
    ということです
    1.08
    もあって
    1.08
     ARISING
    1.08
    antism
    1.06
    peka
    1.02
    がありますが
    1.00
    ：……
    1.00
    uded
    0.98
    そうですが
    0.98
    Activations Density 0.005%

    No Known Activations