© 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-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 10636
    Prev
    Next
    INDEX
    Explanations

    which or who introduces description

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

    set by

    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_31_width_262k_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
    ]$.
    0.46
    ].
    0.45
    ।
    0.45
    }$.
    0.45
    }.
    0.42
    。
    0.42
    ։
    0.41
    %.
    0.40
    '].
    0.40
    }}.
    0.39
    POSITIVE LOGITS
     admittedly
    0.54
     übrigens
    0.38
     recordemos
    0.38
     மிகவும்
    0.37
     incidentally
    0.36
     presumably
    0.35
    !,
    0.33
     quizás
    0.33
    mittedly
    0.33
     vielleicht
    0.33
    Activations Density 0.384%

    No Known Activations