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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 22452
    Prev
    Next
    INDEX
    Explanations

    acid and acidic things

    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_all/layer_41_width_262k_l0_big
    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
     железнодоро
    0.43
    悟空
    0.43
    绒
    0.41
    𒉣
    0.41
    撬
    0.41
    衛星
    0.40
     रोहित
    0.39
     railway
    0.39
     لوبی
    0.38
    ပဲ
    0.38
    POSITIVE LOGITS
     acidic
    2.47
     acid
    2.44
     Acid
    2.30
     acids
    2.25
    酸
    2.25
    Acid
    2.23
     acidity
    2.20
    acid
    2.14
     acidification
    2.02
     Acids
    1.98
    Activations Density 0.019%

    No Known Activations