© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 1582
    Prev
    Next
    INDEX
    Explanations

    geography

    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
     on
    1.05
     empez
    0.94
    ك
    0.93
     efectuar
    0.92
    ب
    0.91
     ética
    0.88
     esenciales
    0.88
     établ
    0.86
     ऑन
    0.85
     adquis
    0.84
    POSITIVE LOGITS
    ,
    1.41
    '
    1.37
     I
    1.34
    ’
    1.21
    _
    1.06
    -
    1.05
    '-
    0.95
    に
    0.95
    ir
    0.92
     geography
    0.91
    Activations Density 0.004%

    No Known Activations