© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5391
    Prev
    Next
    INDEX
    Explanations

    word fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     piace
    0.90
     ἀ
    0.82
     ὁ
    0.80
     nume
    0.76
     fost
    0.76
     accur
    0.75
     vah
    0.74
     haq
    0.74
     ah
    0.73
     やつ
    0.73
    POSITIVE LOGITS
    </b>
    0.60
    ד
    0.59
    __
    0.56
    _,
    0.55
    ッ
    0.54
    --
    0.53
    --)
    0.52
    -.
    0.50
    `
    0.50
    ui
    0.49
    Activations Density 0.023%

    No Known Activations