© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10344
    Prev
    Next
    INDEX
    Explanations

    code delimiters like `*` and `**`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Breg
    0.93
    }}}
    0.90
    pentine
    0.85
     NUS
    0.84
    Couldn
    0.83
    ினி
    0.83
    }},
    0.82
     mời
    0.82
    *{
    0.82
    ‫
    0.82
    POSITIVE LOGITS
     walled
    0.99
     zona
    0.82
     poly
    0.80
    वेद
    0.79
     मोन
    0.78
    <0xB6>
    0.78
     പരാ
    0.76
    dyl
    0.75
     Vern
    0.75
    ποίηση
    0.74
    Activations Density 0.004%

    No Known Activations