© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 597
    Prev
    Next
    INDEX
    Explanations

    path to files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     C
    0.85
     P
    0.84
     E
    0.83
     S
    0.83
     e
    0.81
     men
    0.81
     street
    0.80
     limbs
    0.80
     ev
    0.80
     access
    0.79
    POSITIVE LOGITS
    “(
    1.37
    <unused849>
    1.22
     своей
    1.18
    (“
    1.17
    ("-"
    1.17
    (/(
    1.16
    డానికి
    1.16
    മുള്ള
    1.15
    ((
    1.15
    ('',
    1.15
    Activations Density 0.067%

    No Known Activations