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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 5254
    Prev
    Next
    INDEX
    Explanations

    self-describing, self-contained, self-sustaining

    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_22_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
    -
    1.90
    _
    1.22
    -'
    1.12
    -(
    1.06
    ـ
    1.02
    -}
    1.01
    \_
    1.00
    -*
    1.00
    -‘
    0.99
    -.
    0.96
    POSITIVE LOGITS
    վում
    0.74
     undirected
    0.70
    ையம்
    0.65
    راہیم
    0.65
    ிருக்கும்
    0.64
    ᱑
    0.64
    звание
    0.64
    <unused411>
    0.63
    irected
    0.63
     authored
    0.63
    Activations Density 0.004%

    No Known Activations