© 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. 10-GEMMASCOPE-RES-131K
    7. 70979
    Prev
    Next
    INDEX
    Explanations

    agreement followed by qualification

    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_10/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
    masing
    -1.19
    delivr
    -1.17
    ütze
    -1.15
    ఙ
    -1.15
    Affect
    -1.13
    Tourist
    -1.13
    ükü
    -1.13
    Hermoso
    -1.13
     если
    -1.12
    Zubereitung
    -1.12
    POSITIVE LOGITS
     only
    1.68
     that
    1.64
    You
    1.63
    As
    1.58
     about
    1.58
     people
    1.51
     they
    1.46
     strongly
    1.44
    With
    1.40
     first
    1.38
    Activations Density 0.015%

    No Known Activations