© 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. 12-GEMMASCOPE-2-RES-262K
    7. 5743
    Prev
    Next
    INDEX
    Explanations

    supernatural creatures, beings, battles, forces, powers

    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_12_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
    P
    1.73
    R
    1.66
    T
    1.58
     savior
    1.49
    D
    1.48
    á
    1.46
    M
    1.44
    Potion
    1.42
    C
    1.42
    ți
    1.41
    POSITIVE LOGITS
    na
    1.48
    LEMENT
    1.45
     visant
    1.45
    ﺎ
    1.44
     antérieurs
    1.43
    IE
    1.42
     ainult
    1.42
    ज
    1.41
    ILL
    1.41
    factors
    1.40
    Activations Density 0.003%

    No Known Activations