© 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. 45226
    Prev
    Next
    INDEX
    Explanations

    conservative viewpoints

    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
     calculations
    0.84
     Анд
    0.84
     জর
    0.83
    PAAm
    0.83
    Ps
    0.83
    痨
    0.81
     revelations
    0.81
     corroborated
    0.79
    Hiro
    0.79
     PSR
    0.79
    POSITIVE LOGITS
     conservatives
    0.89
     libertarian
    0.86
     chaleur
    0.84
    T
    0.84
     filmes
    0.83
    Amérique
    0.81
     poudre
    0.80
     Conservatives
    0.79
     tâches
    0.77
     bulunur
    0.77
    Activations Density 0.016%

    No Known Activations