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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 1056
    Prev
    Next
    INDEX
    Explanations

    directly against principles

    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_29_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
    …’
    1.10
     ‘
    1.10
    ?’
    1.03
     …..
    1.01
     ……..
    1.01
    ……”
    1.00
    ’.
    1.00
    ’).
    1.00
    ….
    1.00
     ….
    0.99
    POSITIVE LOGITS
     prioritizing
    0.91
     specifically
    0.89
     referenced
    0.87
     (\"
    0.87
     unspecified
    0.85
     illogical
    0.84
     likened
    0.84
     needing
    0.84
    <unused2169>
    0.82
     logically
    0.81
    Activations Density 0.801%

    No Known Activations