© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108436
    Prev
    Next
    INDEX
    Explanations

    don't hesitate

    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
    diteur
    -0.77
     nive
    -0.77
     ريال
    -0.76
    ziale
    -0.75
    wales
    -0.75
    guenos
    -0.74
    sible
    -0.74
    ╹
    -0.74
     "&
    -0.73
    кви
    -0.71
    POSITIVE LOGITS
     hesitate
    5.16
     hesitation
    4.84
     hesitated
    4.53
     hes
    3.89
     hesitating
    3.66
     Hes
    3.38
    Hes
    3.30
     hesitant
    3.17
    hes
    3.02
     hés
    2.89
    Activations Density 0.024%

    No Known Activations