© 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-IT
    3. 13-GEMMASCOPE-2-RES-65K
    4. 261
    Prev
    Next
    INDEX
    Explanations

    lingers long after the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     driving
    1.07
     dealing
    1.07
     leading
    1.04
     turning
    1.03
    ↵↵
    1.00
     related
    0.99
     avoiding
    0.97
     posing
    0.96
     potential
    0.95
     business
    0.95
    POSITIVE LOGITS
    atthavidu
    1.93
     smoothedseries
    1.93
    <unused2895>
    1.93
    𒀬
    1.92
    sadurdu
    1.92
    syncEach
    1.92
    <unused5105>
    1.92
    <0x02>
    1.92
    𒑎
    1.92
    𒇹
    1.92
    Activations Density 0.000%

    No Known Activations