Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 1820
    Prev
    Next
    INDEX
    Explanations

    the [Capitalized Word]

    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_17_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
    Г
    0.94
    and
    0.82
    ating
    0.80
    Ü
    0.76
    0
    0.73
    а
    0.71
    1
    0.71
     determinada
    0.70
    И
    0.69
    が
    0.69
    POSITIVE LOGITS
    mselves
    1.39
    ophylline
    1.32
    atrical
    1.31
    orems
    1.23
    oretically
    1.21
    odore
    1.15
    jenigen
    1.10
    matic
    1.05
    lma
    1.02
    oretic
    0.95
    Activations Density 0.759%

    No Known Activations