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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7908
    Prev
    Next
    INDEX
    Explanations

    suicidal thoughts or behavior

    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
    }.
    1.48
     Epsom
    1.46
    $\\
    1.45
    teil
    1.44
    }$
    1.41
    })
    1.41
    }}$,
    1.41
    ];
    1.40
     olacak
    1.38
    POSITIVE LOGITS
    اً
    1.85
     وعلى
    1.77
    лна
    1.70
    ας
    1.53
    ك
    1.53
     위해
    1.49
    śmy
    1.49
    ير
    1.46
    য়া
    1.46
    ەتی
    1.46
    Activations Density 0.010%

    No Known Activations