© 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. 68189
    Prev
    Next
    INDEX
    Explanations

    Freud psychoanalysis analytic

    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
     Then
    -2.53
    ࿚
    -2.38
     So
    -2.33
     For
    -2.33
    蕻
    -2.31
     уровня
    -2.25
     Their
    -2.16
     suas
    -2.13
     видимо
    -2.09
     Also
    -2.08
    POSITIVE LOGITS
    梣
    2.63
    鬭
    2.53
     godziny
    2.47
    ጪ
    2.36
    2
    2.28
    the
    2.27
    酲
    2.22
    .
    2.20
    鯓
    2.19
     التالي
    2.16
    Activations Density 0.005%

    No Known Activations