© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 10725
    Prev
    Next
    INDEX
    Explanations

    code statements ending in )”

    np_acts-logits-general · gemini-2.5-flash-lite

    closing code block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    }}}
    0.42
    }^*
    0.42
    //}
    0.41
    })}
    0.40
    }//
    0.40
    }}},
    0.40
    }_{+}
    0.39
    .}
    0.39
     *}(
    0.39
    }
    0.39
    POSITIVE LOGITS
     Fü
    0.39
    exempt
    0.38
    पित
    0.38
    πε
    0.37
    秘书
    0.37
    ChessBot
    0.36
    랬
    0.36
    improvement
    0.36
    uglify
    0.36
     accrued
    0.35
    Activations Density 0.000%

    No Known Activations