© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 8601
    Prev
    Next
    INDEX
    Explanations

    lead exposure and contamination

    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
     blinked
    0.53
    Drone
    0.52
    <0xA4>
    0.52
    ধর্ম
    0.51
     கோவை
    0.50
    ванта
    0.50
     beamed
    0.49
    пре
    0.49
    কথা
    0.49
    ники
    0.48
    POSITIVE LOGITS
    的老
    0.49
     विषा
    0.46
    n
    0.46
    。
    0.42
     liga
    0.41
     mayor
    0.41
    }
    0.41
    凶
    0.41
    ”)
    0.40
    े
    0.40
    Activations Density 0.001%

    No Known Activations