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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 106
    Prev
    Next
    INDEX
    Explanations

    acid, C, peroxide

    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
     (
    0.24
    uero
    0.23
    $/../../
    0.23
    igraphic
    0.22
     यशस्वी
    0.22
    jacoco
    0.22
     interstices
    0.22
    वाणी
    0.21
     जीव
    0.21
    yaml
    0.21
    POSITIVE LOGITS
    ↵
    0.38
    ي
    0.38
    }
    0.35
    </sup>
    0.30
    </b>
    0.30
     recommandé
    0.29
    "},
    0.29
    2
    0.29
    for
    0.29
     Bestellung
    0.29
    Activations Density 0.252%

    No Known Activations