© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8643
    Prev
    Next
    INDEX
    Explanations

    transparent

    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
    с
    2.05
    ↵
    1.85
    е
    1.75
    у
    1.74
    ،
    1.66
    ない
    1.59
    มี
    1.57
    何を
    1.57
    urring
    1.50
     juist
    1.48
    POSITIVE LOGITS
     gorges
    1.56
    }=$
    1.52
    }));
    1.51
     triads
    1.50
    页面存档备份
    1.44
    ණය
    1.43
     hydrox
    1.42
    িলিয়া
    1.42
     waveguides
    1.39
    }$$
    1.38
    Activations Density 0.006%

    No Known Activations