© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 701
    Prev
    Next
    INDEX
    Explanations

    message: Free

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

    function arguments

    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_53_width_65k_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
     Unless
    0.38
     〢
    0.37
    agangan
    0.36
     уены
    0.36
    Unless
    0.36
     يكون
    0.35
     indulging
    0.35
     وطالبات
    0.34
    除非
    0.34
    ்சைடு
    0.33
    POSITIVE LOGITS
    ंड
    0.36
    不等
    0.33
    th
    0.32
     ['(?
    0.32
    onesome
    0.31
    j
    0.31
    ន្តែ
    0.31
    don
    0.30
    firm
    0.30
    ="__
    0.30
    Activations Density 0.169%

    No Known Activations