© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 10833
    Prev
    Next
    INDEX
    Explanations

    another followed by a new item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_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
    };
    1.66
     demás
    1.54
    }));
    1.48
    )$
    1.47
    ções
    1.47
    }{\
    1.45
    }"]
    1.45
    )}}\
    1.43
     noche
    1.38
    }))
    1.38
    POSITIVE LOGITS
    ید
    1.71
    ای
    1.62
    да
    1.56
    are
    1.55
    ment
    1.53
    ಲ್ಲಿ
    1.51
    ام
    1.50
    ದ
    1.45
    ून
    1.44
    торой
    1.43
    Activations Density 0.007%

    No Known Activations