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-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 3482
    Prev
    Next
    INDEX
    Explanations

    clauses ending in commas, followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    that
    0.58
    _
    0.58
    ter
    0.52
    as
    0.50
    hitth
    0.50
    a
    0.49
    d
    0.48
    tem
    0.47
    typen
    0.47
     Einf
    0.47
    POSITIVE LOGITS
     been
    0.66
     be
    0.64
     were
    0.63
     in
    0.59
     \
    0.56
     are
    0.55
     is
    0.54
    <!
    0.54
     accidentally
    0.54
     migrate
    0.53
    Activations Density 0.010%

    No Known Activations