© 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. 234
    Prev
    Next
    INDEX
    Explanations

    code structure

    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
     subversive
    0.74
     바
    0.72
    𝑤
    0.72
     more
    0.70
     seemingly
    0.69
    &+
    0.69
     combinations
    0.67
    obytes
    0.66
    lores
    0.66
     Hermione
    0.64
    POSITIVE LOGITS
     vidrio
    0.80
     При
    0.77
     Når
    0.74
     Carpet
    0.74
     संप
    0.73
     জন
    0.73
     مس
    0.72
    ografico
    0.71
    1
    0.71
     மாறிய
    0.71
    Activations Density 0.569%

    No Known Activations