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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1536
    Prev
    Next
    INDEX
    Explanations

    links ending in )

    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_16k_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
     optimize
    0.77
     optimizing
    0.65
     required
    0.64
     efficient
    0.63
     be
    0.62
     acetaldehyde
    0.62
    ীদার
    0.62
     `<`,
    0.60
     топли
    0.60
    всем
    0.59
    POSITIVE LOGITS
     Print
    0.95
     )
    0.90
    Lloyd
    0.90
     गौरतलब
    0.89
     Click
    0.86
    Print
    0.85
    ism
    0.85
    ')
    0.83
    RC
    0.82
     ).
    0.81
    Activations Density 0.194%

    No Known Activations