© 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. 162806
    Prev
    Next
    INDEX
    Explanations

    addresses and city/state information

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

    comorbidities and conditions

    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
     travaux
    0.51
     Kenyans
    0.48
     regl
    0.48
     Renal
    0.48
     रुग्ण
    0.47
     semblable
    0.47
     predstav
    0.46
     $\|\
    0.46
     appalled
    0.46
     impair
    0.45
    POSITIVE LOGITS
    {
    0.49
    9
    0.46
    SIL
    0.45
    Historical
    0.45
    TITLE
    0.44
     ""
    0.43
    FirstResponder
    0.43
    Franklin
    0.42
    сили
    0.41
    гай
    0.41
    Activations Density 0.002%

    No Known Activations