© 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. 28315
    Prev
    Next
    INDEX
    Explanations

    United States geography

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

    politics

    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
     монет
    0.33
    季节
    0.31
    ListAdapter
    0.31
    迟
    0.31
    房价
    0.30
    긁
    0.30
    Phill
    0.30
     बुन
    0.30
    బ్బు
    0.30
     Phill
    0.29
    POSITIVE LOGITS
    verb
    0.36
     Footage
    0.34
    aset
    0.33
     cih
    0.33
    asing
    0.33
    ("[
    0.32
     voluto
    0.32
     pathogenesis
    0.32
     ofens
    0.32
     governing
    0.31
    Activations Density 0.025%

    No Known Activations