© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54201
    Prev
    Next
    INDEX
    Explanations

    sounds like a description

    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_65k_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
    compareTo
    0.36
    洊
    0.33
     নজর
    0.33
     ಮೆ
    0.33
     ನಡೆ
    0.32
    owied
    0.32
    }_\
    0.32
    vastatin
    0.32
    &=
    0.32
    >′
    0.32
    POSITIVE LOGITS
     sounds
    2.08
     Sounds
    2.00
    Sounds
    1.95
    sounds
    1.86
     зву
    1.59
     klingt
    1.48
     suena
    1.46
     SOUND
    1.34
     sound
    1.33
     sonidos
    1.33
    Activations Density 0.104%

    No Known Activations