© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 8292
    Prev
    Next
    INDEX
    Explanations

    Representation

    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
    ä
    1.48
     on
    1.27
    ки
    1.27
     amplio
    1.26
    ف
    1.18
    し
    1.14
    ления
    1.13
    大
    1.09
     to
    1.06
     avión
    1.05
    POSITIVE LOGITS
    ’
    1.02
    ר
    0.93
    the
    0.91
    ur
    0.90
    al
    0.89
    Representation
    0.83
    ש
    0.83
     Representation
    0.82
     Representations
    0.81
     Represent
    0.81
    Activations Density 0.047%

    No Known Activations