© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3599
    Prev
    Next
    INDEX
    Explanations

    contact information

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

    credit card, autonomous, ai, del taco, whale

    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
    \&
    0.41
    \#
    0.41
    \'
    0.40
     \...
    0.40
    \'{
    0.39
    னால்
    0.38
    会让
    0.37
    ార్లు
    0.36
    \;
    0.35
     البيت
    0.35
    POSITIVE LOGITS
    servic
    0.86
     servic
    0.82
     watert
    0.82
     earthqu
    0.81
     usern
    0.81
     behavi
    0.81
     powert
    0.79
     onem
    0.79
     clust
    0.79
     volunte
    0.77
    Activations Density 0.125%

    No Known Activations