© 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. 108254
    Prev
    Next
    INDEX
    Explanations

    given or each

    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
    many
    -0.97
    such
    -0.96
    SOCI
    -0.91
     lediglich
    -0.90
     verein
    -0.90
     tercio
    -0.89
    plet
    -0.88
     Such
    -0.88
     such
    -0.88
     بچ
    -0.88
    POSITIVE LOGITS
     each
    2.08
     indicated
    1.51
     given
    1.38
     following
    1.30
     if
    1.20
    given
    1.19
    each
    1.07
     specified
    1.07
     chaque
    1.03
     chacune
    1.03
    Activations Density 0.073%

    No Known Activations