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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 34335
    Prev
    Next
    INDEX
    Explanations

    `a`, A, i, Y followed by punctuation

    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_40_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
    }=-
    0.38
    oweit
    0.38
    ologically
    0.37
     של
    0.37
    }=\
    0.37
    ol
    0.37
    }=-\
    0.37
    ialmente
    0.36
    istemas
    0.36
    ल
    0.35
    POSITIVE LOGITS
     ensue
    0.35
     DON
    0.35
     인해
    0.34
     itself
    0.32
    ؔ
    0.31
    的内容
    0.31
     glazed
    0.30
    凭
    0.30
    …
    0.30
     butt
    0.30
    Activations Density 0.019%

    No Known Activations