© 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. 31-GEMMASCOPE-2-RES-262K
    4. 71881
    Prev
    Next
    INDEX
    Explanations

    negation, specific commands, and descriptive categories

    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_31_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
     maand
    0.53
     месе
    0.51
    s
    0.49
     herbs
    0.49
     bonding
    0.48
     mutant
    0.45
     recordings
    0.42
     mes
    0.42
     pandemics
    0.41
     gusto
    0.41
    POSITIVE LOGITS
    imbabwe
    0.54
    ikal
    0.48
    ahkan
    0.47
    ikiem
    0.46
    3
    0.46
    utiliser
    0.45
    anmar
    0.45
    ukannya
    0.45
    buscar
    0.44
    immer
    0.44
    Activations Density 0.001%

    No Known Activations