© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 115141
    Prev
    Next
    INDEX
    Explanations

    print out and distribute

    np_acts-logits-general · gemini-2.5-flash-lite

    time relative to current events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymbol
    0.49
    ib
    0.47
    ти
    0.45
    ologia
    0.45
    ifilm
    0.42
    ீ
    0.42
    䂝
    0.41
    im
    0.41
     simbol
    0.41
    ile
    0.41
    POSITIVE LOGITS
    RIBUTION
    0.52
     CONCLUS
    0.47
     EXAMINATION
    0.47
     EACH
    0.47
     empêcher
    0.47
     incend
    0.46
     trillions
    0.46
     réduite
    0.46
     উচ্ছ
    0.46
     DISTRIBUTION
    0.45
    Activations Density 0.000%

    No Known Activations