Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169179
    Prev
    Next
    INDEX
    Explanations

    choice

    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_31_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
    }}-\
    0.63
    }+\
    0.51
     ಯಾವುದ
    0.50
     ಸಂಬ
    0.49
     दिरहम
    0.49
    மஹ
    0.48
    юнча
    0.48
     ಸ್ವಲ್ಪ
    0.48
     ممکن
    0.48
     لان
    0.48
    POSITIVE LOGITS
     =
    0.49
    ia
    0.49
     
    0.48
    B
    0.46
    um
    0.46
     mo
    0.45
     stata
    0.44
    。
    0.44
    si
    0.43
     daughter
    0.43
    Activations Density 0.000%

    No Known Activations