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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10226
    Prev
    Next
    INDEX
    Explanations

    CBT and DBT

    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_22_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
     Premises
    0.83
     Indexes
    0.83
    டியா
    0.83
     함
    0.79
     විශේෂ
    0.77
     unm
    0.77
    नास
    0.77
     පුද්ග
    0.76
     මිනි
    0.75
    ?>
    0.75
    POSITIVE LOGITS
    citep
    1.32
    eqref
    1.15
    ጮ
    1.11
    cite
    1.09
     Babu
    1.06
    Harper
    1.04
     breeze
    1.03
    Bab
    1.00
    Alberto
    1.00
    Roh
    0.98
    Activations Density 0.007%

    No Known Activations