© 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. 16-GEMMASCOPE-2-RES-262K
    7. 119791
    Prev
    Next
    INDEX
    Explanations

    philosophy, seminars, China, mirrors

    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_16_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
    }=
    0.57
     దు
    0.54
    ária
    0.54
    isant
    0.53
    agner
    0.52
    }=\
    0.52
     tortues
    0.51
    eten
    0.49
    ints
    0.49
     හෝ
    0.49
    POSITIVE LOGITS
    まず
    0.60
    ն
    0.57
    an
    0.54
     I
    0.54
    ה
    0.54
    ar
    0.54
    ру
    0.54
    ー
    0.54
    Research
    0.53
     sejak
    0.53
    Activations Density 0.000%

    No Known Activations