© 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. 158282
    Prev
    Next
    INDEX
    Explanations

    names and common entities

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

    the type / reason why / bacterial Strain

    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
    цем
    0.48
    戎
    0.48
    гада
    0.47
     marchés
    0.47
    τε
    0.46
     animé
    0.45
     piens
    0.43
    ugoslav
    0.43
     название
    0.43
    मला
    0.43
    POSITIVE LOGITS
     或者
    0.48
     hierarchy
    0.48
    hierarchy
    0.48
     ඒ
    0.42
    bottle
    0.41
     หรือ
    0.40
    IAL
    0.40
     hierarch
    0.40
     आईआईटी
    0.40
     జన్
    0.40
    Activations Density 0.002%

    No Known Activations