© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3166
    Prev
    Next
    INDEX
    Explanations

    necessary capabilities

    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_31_width_16k_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
    way
    0.60
    when
    0.58
     নির্ভরশীল
    0.58
     way
    0.57
     when
    0.57
    which
    0.56
     Way
    0.56
    }
    0.56
     Significance
    0.55
    '
    0.55
    POSITIVE LOGITS
     necessary
    2.23
    necessary
    1.92
     nécessaires
    1.89
     necessários
    1.86
     nécessaire
    1.85
     необходи
    1.84
     necessário
    1.84
     необходимые
    1.83
     необхід
    1.80
     необходимых
    1.80
    Activations Density 0.409%

    No Known Activations