© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1480
    Prev
    Next
    INDEX
    Explanations

    instead of

    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
    <blockquote>
    0.98
     although
    0.97
     basically
    0.94
     Basically
    0.90
     Although
    0.89
     mainly
    0.88
     wherever
    0.84
    <strong>
    0.83
     whenever
    0.83
    Basically
    0.81
    POSITIVE LOGITS
    ^{\#}\
    1.24
    plätze
    1.22
    lá
    1.16
    ué
    1.13
     vý
    1.10
    ugía
    1.08
    uées
    1.07
     órdenes
    1.07
     dě
    1.06
     günst
    1.06
    Activations Density 0.023%

    No Known Activations