© 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. 188722
    Prev
    Next
    INDEX
    Explanations

    personal data and accounts

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

    exploitation and abuse

    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
    ل
    0.53
    erate
    0.47
    eng
    0.47
    資格
    0.47
    t
    0.46
    aktu
    0.45
    pall
    0.45
    াল
    0.45
    ం
    0.45
    規定
    0.45
    POSITIVE LOGITS
     offensively
    0.46
     pengh
    0.45
     historically
    0.45
     installment
    0.45
     prosperous
    0.45
     berj
    0.45
     বিহ
    0.45
     millionaire
    0.44
     conveniently
    0.44
     prosper
    0.43
    Activations Density 0.001%

    No Known Activations