© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10456
    Prev
    Next
    INDEX
    Explanations

    code definitions and structure

    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_17_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
     bloodshed
    1.15
    <unused2223>
    1.05
    䢀
    1.04
    <unused2121>
    1.04
     clichés
    1.03
     garnished
    1.02
    ၷ
    1.02
     meaningless
    1.02
     intraven
    1.01
    <unused2148>
    1.00
    POSITIVE LOGITS
    our
    1.10
    old
    1.07
    ion
    1.05
    assess
    1.03
    inner
    1.02
    iter
    1.00
    outer
    1.00
    at
    0.98
    pos
    0.97
    ab
    0.96
    Activations Density 0.007%

    No Known Activations