© 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
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 526
    Prev
    Next
    INDEX
    Explanations

    code delimiters and non-English text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    Phir
    0.63
    Featuring
    0.59
     moon
    0.58
    떤
    0.57
     exploratory
    0.57
     Daph
    0.57
    getBlueTeam
    0.57
     Featuring
    0.56
     siting
    0.56
     phyll
    0.56
    POSITIVE LOGITS
     }
    0.74
    )}
    0.65
    }\}
    0.62
    })}
    0.62
    }});
    0.61
     },
    0.60
    <unused199>
    0.60
    }`,
    0.59
    }},
    0.59
    }@
    0.59
    Activations Density 0.010%

    No Known Activations