© 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. 34-GEMMASCOPE-RES-131K
    7. 78566
    Prev
    Next
    INDEX
    Explanations

    gain or lose

    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
    aconda
    -0.91
     dealing
    -0.80
    jMenuItem
    -0.79
    sistance
    -0.79
     tưởng
    -0.77
     lequel
    -0.77
    SSH
    -0.76
     են
    -0.75
    }+(
    -0.75
     Tampoco
    -0.75
    POSITIVE LOGITS
     lose
    1.63
     Lose
    1.41
     теря
    1.38
    Lose
    1.29
    everything
    1.21
    lose
    1.20
    Everything
    1.10
     gain
    1.09
     Gain
    1.07
     verlieren
    1.07
    Activations Density 0.013%

    No Known Activations