© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 896
    Prev
    Next
    INDEX
    Explanations

    the letter sequence `cl`

    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
     বির
    0.41
    MiddleLine
    0.41
     واح
    0.39
     sıra
    0.38
    糈
    0.37
     Державний
    0.36
    岁月
    0.36
    關注
    0.35
     Aqueous
    0.35
    珹
    0.35
    POSITIVE LOGITS
    Cl
    0.97
     Cl
    0.96
     클
    0.95
     cl
    0.95
     CL
    0.89
     क्ल
    0.85
    cl
    0.84
     کل
    0.80
    클
    0.76
     Cler
    0.74
    Activations Density 0.032%

    No Known Activations