© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 735
    Prev
    Next
    INDEX
    Explanations

    as followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ts
    2.65
    to
    2.45
    <bos>
    2.16
    trim
    2.07
    ty
    2.03
    tr
    2.01
    ta
    2.00
    ton
    1.95
    turn
    1.94
    t
    1.93
    POSITIVE LOGITS
    ymmet
    3.37
     opposed
    2.79
    phalt
    2.75
     dusk
    2.71
    pergillus
    2.69
    ymmetric
    2.62
    ymmetries
    2.61
    ymmetrical
    2.57
    sembling
    2.56
    pekte
    2.54
    Activations Density 0.672%

    No Known Activations