© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10037
    Prev
    Next
    INDEX
    Explanations

    explain that

    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_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
     described
    0.93
    erequisite
    0.86
    rizable
    0.85
     origina
    0.85
     mehreren
    0.85
    <unused2117>
    0.84
    訲
    0.83
    жением
    0.83
    乆
    0.83
    様専用
    0.82
    POSITIVE LOGITS
     nifty
    2.06
     pesky
    2.00
     nasty
    1.89
     trusty
    1.89
     whopping
    1.77
     hefty
    1.74
     cheeky
    1.74
     goodies
    1.73
     paltry
    1.73
     sneaky
    1.69
    Activations Density 0.094%

    No Known Activations