© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 838
    Prev
    Next
    INDEX
    Explanations

    Organization and focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
     ஆகியோர்
    1.01
    拥有
    0.93
     содержа
    0.87
     utilisent
    0.86
    擁有
    0.83
     possèdent
    0.82
    ገኙ
    0.79
    )[:
    0.79
     présentent
    0.77
    contain
    0.77
    POSITIVE LOGITS
     isn
    2.21
     varies
    2.18
     remains
    2.14
     depends
    2.12
     seems
    2.06
     hasn
    1.92
     awaits
    1.89
     is
    1.89
     cannot
    1.84
     persists
    1.84
    Activations Density 1.700%

    No Known Activations