© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 42050
    Prev
    Next
    INDEX
    Explanations

    negation; prohibitions; must

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    훗
    0.77
    áno
    0.76
     "\"
    0.75
     powied
    0.75
     volna
    0.74
    //"
    0.74
     drob
    0.72
    {};
    0.71
     quello
    0.70
     αρχ
    0.70
    POSITIVE LOGITS
    ut
    1.39
    </h4>
    1.13
    </h2>
    1.09
    t
    1.09
    ↵
    1.02
    ↵↵
    0.99
    </h3>
    0.97
    </b>
    0.95
    וס
    0.95
    </sub>
    0.93
    Activations Density 0.000%

    No Known Activations