© 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-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 242
    Prev
    Next
    INDEX
    Explanations

    try to then a verb

    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
     S
    0.83
     No
    0.76
    no
    0.73
     Wid
    0.72
    _-
    0.71
     ኤ
    0.71
     Up
    0.69
     staring
    0.66
     parked
    0.66
    No
    0.66
    POSITIVE LOGITS
     desesper
    1.30
     imitate
    1.19
    <unused388>
    1.18
    <unused524>
    1.16
    賚
    1.16
    <unused1966>
    1.15
    ッシュ
    1.15
    <unused1955>
    1.15
    <unused384>
    1.13
    
    1.12
    Activations Density 0.615%

    No Known Activations