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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7534
    Prev
    Next
    INDEX
    Explanations

    no followed by descriptor

    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_9_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
    Definitely
    2.40
    いる
    2.34
    curr
    2.32
    tive
    2.24
    remaining
    2.20
     scintillation
    2.17
    𝓪
    2.12
     kajian
    2.10
    มีการ
    2.01
     निवेदन
    2.00
    POSITIVE LOGITS
    که
    2.46
    ﻦ
    2.35
    ﻢ
    2.33
    amiento
    2.18
     decade
    2.17
    ado
    2.15
    le
    2.11
     afraid
    2.11
     damn
    2.10
     aware
    2.07
    Activations Density 0.004%

    No Known Activations