© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1479
    Prev
    Next
    INDEX
    Explanations

    cal followed by various suffixes

    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_40_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
     έναν
    0.44
    ップ
    0.41
     Wexford
    0.41
     قریب
    0.41
    angun
    0.41
    )|^{
    0.41
    겅
    0.41
    BinBuf
    0.41
    går
    0.40
    ある
    0.40
    POSITIVE LOGITS
    Cal
    1.18
     Cal
    1.14
     cal
    1.11
    cal
    1.08
     CAL
    0.98
     ক্যাল
    0.91
    CAL
    0.89
    캘
    0.72
     Cali
    0.70
     calorimeter
    0.70
    Activations Density 0.022%

    No Known Activations