© 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. 143125
    Prev
    Next
    INDEX
    Explanations

    Aristotle, ZebraBI, school, older

    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
    레
    0.47
    ด้วย
    0.46
    데
    0.45
     विषया
    0.43
    KNOWN
    0.42
    ESOME
    0.42
    EXE
    0.41
    BtnPanel
    0.41
    టు
    0.41
     добав
    0.40
    POSITIVE LOGITS
     máquina
    0.45
    汼
    0.43
     traduire
    0.42
     diar
    0.42
    ciąż
    0.41
    omie
    0.41
    这时候
    0.41
     illuminate
    0.40
    rène
    0.40
     macchina
    0.40
    Activations Density 0.004%

    No Known Activations