© 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. 31-GEMMASCOPE-2-RES-65K
    7. 62369
    Prev
    Next
    INDEX
    Explanations

    Dark City

    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_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
     пациен
    0.51
     весьма
    0.48
     alkoh
    0.44
    イギリス
    0.44
     pacient
    0.43
    🎂
    0.42
     なかっ
    0.42
     осо
    0.42
    BleStatus
    0.42
     doloribus
    0.42
    POSITIVE LOGITS
     im
    0.42
     over
    0.40
     on
    0.40
    licts
    0.39
    的
    0.39
    िट
    0.39
    ାଇ
    0.39
     infrastructure
    0.39
     reconstruction
    0.38
    <0x9B>
    0.38
    Activations Density 0.005%

    No Known Activations