© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2349
    Prev
    Next
    INDEX
    Explanations

    if the remainder

    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_13_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
    .
    1.22
     e
    1.16
     all
    1.11
     ALL
    1.06
     be
    1.05
     do
    1.02
     os
    0.99
     Make
    0.99
     na
    0.98
    ...
    0.98
    POSITIVE LOGITS
    unexpected
    1.87
    <unused147>
    1.81
    zmdi
    1.80
    slidesPer
    1.76
    <unused1626>
    1.75
    dayspecial
    1.74
    <unused1168>
    1.73
    striées
    1.73
    lensFlare
    1.73
    <unused298>
    1.72
    Activations Density 0.000%

    No Known Activations