© 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. 78193
    Prev
    Next
    INDEX
    Explanations

    hold back

    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
     hold
    -2.05
    Hold
    -1.80
    hold
    -1.79
     Hold
    -1.79
     HOLD
    -1.69
     holding
    -1.69
    HOLD
    -1.67
     Holds
    -1.60
     holds
    -1.60
     held
    -1.58
    POSITIVE LOGITS
     back
    2.48
    back
    1.63
    Back
    1.45
    BACK
    1.22
     BACK
    1.20
     Back
    1.15
     назад
    1.05
     tilbake
    1.04
     zurück
    0.98
     indietro
    0.97
    Activations Density 0.016%

    No Known Activations