© 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. 24-GEMMASCOPE-2-RES-262K
    7. 9048
    Prev
    Next
    INDEX
    Explanations

    plataforma, comunidad, aplicación, distribución de conceptos

    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_24_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
    0.64
    s
    0.57
    ym
    0.55
    yd
    0.54
    ytu
    0.54
    g
    0.54
     hoping
    0.53
    utors
    0.53
     -
    0.52
     &
    0.52
    POSITIVE LOGITS
     adicional
    0.87
     sincron
    0.85
     altamente
    0.85
     espiritual
    0.83
     ocult
    0.81
     filosóf
    0.79
     compless
    0.79
     espacial
    0.79
     sindical
    0.78
     sensorial
    0.78
    Activations Density 0.087%

    No Known Activations