© 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. 44208
    Prev
    Next
    INDEX
    Explanations

    doll houses

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

    standards and compliance

    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
    :\
    0.49
     يعني
    0.46
    .\
    0.46
    :
    0.46
    —
    0.44
     CNBC
    0.43
     حكم
    0.43
     showers
    0.42
    \
    0.42
    ke
    0.42
    POSITIVE LOGITS
     opportunità
    0.52
     permettre
    0.52
     postérieure
    0.52
     conoscenze
    0.50
     vati
    0.50
    いますが
    0.48
     오늘도
    0.48
     fou
    0.48
     americana
    0.47
     strutture
    0.47
    Activations Density 0.000%

    No Known Activations