© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199190
    Prev
    Next
    INDEX
    Explanations

    Schizophrenia, rhinos, October

    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
    敉
    0.44
    adjacency
    0.44
    startIndex
    0.44
     sparsim
    0.43
    apabb
    0.43
    өм
    0.41
    рида
    0.40
    を使った
    0.40
    ோ
    0.40
    そも
    0.39
    POSITIVE LOGITS
     are
    0.47
     अगर
    0.47
     vaccinated
    0.45
     will
    0.42
     biasanya
    0.42
     futuro
    0.42
     معمول
    0.41
     if
    0.41
    如果
    0.39
     without
    0.39
    Activations Density 0.007%

    No Known Activations