© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32481
    Prev
    Next
    INDEX
    Explanations

    mental health and policy

    np_acts-logits-general · gemini-2.5-flash-lite

    cooking skill, development workflow, data analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initiate
    0.57
     broaden
    0.53
     commence
    0.50
     incorporate
    0.49
     činjen
    0.49
    ]
    0.48
     elucidate
    0.45
    ])
    0.45
     purport
    0.45
     broadened
    0.45
    POSITIVE LOGITS
     महीने
    0.47
     cupcake
    0.47
    messe
    0.46
     Book
    0.45
    わからない
    0.45
    Book
    0.45
    ம்மா
    0.44
     कहकर
    0.44
    iterator
    0.43
    ító
    0.43
    Activations Density 0.000%

    No Known Activations