© 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. 216976
    Prev
    Next
    INDEX
    Explanations

    heralded thebottom of theSF Dwelling

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

    interference pattern

    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
     bundan
    0.49
     Grande
    0.49
     pracę
    0.47
     خ
    0.45
     tanıt
    0.45
     Collier
    0.45
     peut
    0.44
    ্যাশ
    0.44
     professor
    0.43
     verr
    0.43
    POSITIVE LOGITS
    partials
    0.52
    ，
    0.52
    aaS
    0.48
    メカ
    0.47
     ដែល
    0.46
    ，$
    0.43
    aku
    0.43
    romad
    0.43
    NaCl
    0.42
    rbac
    0.42
    Activations Density 0.000%

    No Known Activations