© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 138
    Prev
    Next
    INDEX
    Explanations

    concepts following "of"

    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
    to
    1.33
    of
    1.28
    It
    1.14
    Of
    1.14
    D
    1.13
    O
    1.11
    I
    1.10
    no
    1.05
     of
    1.03
     Of
    1.02
    POSITIVE LOGITS
    <unused6>
    1.26
    <unused2051>
    1.17
    𒐞
    1.16
    <unused1918>
    1.15
    𒂃
    1.15
    <unused698>
    1.15
    <unused288>
    1.14
    <unused159>
    1.14
    <unused1619>
    1.14
    <unused1643>
    1.14
    Activations Density 1.328%

    No Known Activations