© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 42173
    Prev
    Next
    INDEX
    Explanations

    plot twist

    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
    ING
    0.51
    作物
    0.47
     }
    0.46
     be
    0.46
    星
    0.45
    }
    0.45
    </sup>
    0.45
    F
    0.44
    র্তি
    0.44
    ASTIC
    0.43
    POSITIVE LOGITS
    ismatch
    0.57
    k
    0.52
    قام
    0.50
    ată
    0.49
    ategy
    0.48
    غب
    0.48
    جاب
    0.48
    ongs
    0.46
    attacks
    0.46
    وس
    0.46
    Activations Density 0.000%

    No Known Activations