© 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. 417
    Prev
    Next
    INDEX
    Explanations

    the nearest integer

    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
    ,
    1.24
    ،
    1.13
    -
    1.03
    ，
    0.96
     ن
    0.93
    、
    0.88
     (
    0.86
     No
    0.85
     من
    0.84
     Happy
    0.81
    POSITIVE LOGITS
     તેમણે
    1.28
     việc
    1.21
     다른
    1.17
    ඪ
    1.16
    𒋗
    1.15
     സെക്ര
    1.15
    )})$
    1.13
    敤
    1.11
     관련된
    1.11
     국내
    1.10
    Activations Density 0.001%

    No Known Activations