© 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. 31733
    Prev
    Next
    INDEX
    Explanations

    acts of harm or illegality

    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
    Data
    0.75
    As
    0.72
    Bill
    0.71
     her
    0.70
     colleagues
    0.70
    IN
    0.69
    d
    0.69
    Q
    0.68
    EN
    0.66
    En
    0.66
    POSITIVE LOGITS
    </h3>
    0.85
    </i>
    0.85
    ка
    0.85
    </b>
    0.84
    </a>
    0.83
    ні
    0.80
    は約
    0.78
    ፦
    0.78
    ።
    0.77
    </span>
    0.76
    Activations Density 0.012%

    No Known Activations