© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5174
    Prev
    Next
    INDEX
    Explanations

    executing commands or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    <em>
    1.23
    <code>
    1.23
    <i>
    1.17
    。《
    1.10
    <sup>
    1.10
    .“
    1.01
    <strong>
    1.00
    、《
    0.99
    ‪
    0.98
    ¹.
    0.98
    POSITIVE LOGITS
    ↵
    2.00
    ...!
    1.12
    }
    1.04
    !}
    1.04
    }...
    1.03
     }
    1.03
     ㅎㅎ
    1.01
    }}
    0.98
    ...]
    0.97
    ...'
    0.96
    Activations Density 0.853%

    No Known Activations