© 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. 231451
    Prev
    Next
    INDEX
    Explanations

    son, web, PICK, safety, non-English scripts

    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
     ["
    0.52
     ia
    0.48
     )
    0.47
    []
    0.47
     ]
    0.46
     umożliw
    0.46
     supp
    0.45
     css
    0.44
     Cork
    0.44
     stylistic
    0.44
    POSITIVE LOGITS
     मिळाले
    0.54
    एच
    0.53
    ար
    0.51
    𝗹
    0.51
    лета
    0.50
    額
    0.50
    𝗸
    0.49
    apek
    0.49
    成功
    0.49
    BUSINESS
    0.49
    Activations Density 0.001%

    No Known Activations