© 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. 44619
    Prev
    Next
    INDEX
    Explanations

    following an action

    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
     is
    -2.55
    {
    -1.83
    >
    -1.79
     The
    -1.72
    =
    -1.63
     same
    -1.51
     präsenti
    -1.42
     It
    -1.39
    ''
    -1.39
    l
    -1.38
    POSITIVE LOGITS
     of
    1.55
    sich
    1.49
     possíveis
    1.47
     for
    1.44
    ’，
    1.43
    炱
    1.43
    },
    1.38
     jaunes
    1.34
     penyanyi
    1.34
     okolí
    1.34
    Activations Density 0.096%

    No Known Activations