© 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. 225589
    Prev
    Next
    INDEX
    Explanations

    website, linked, printing, inline

    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
    试验
    0.51
    zenie
    0.50
    vention
    0.49
    воды
    0.48
    ní
    0.47
    梂
    0.47
     تبقى
    0.46
     témoign
    0.46
     సీఎం
    0.46
    ச்சின்ன
    0.45
    POSITIVE LOGITS
    ט
    0.57
     PRESSURE
    0.54
    ұ
    0.46
    q
    0.46
     υψη
    0.45
    रियल
    0.45
    un
    0.45
     Pressure
    0.45
     لنک
    0.44
     at
    0.44
    Activations Density 0.002%

    No Known Activations