© 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-262K
    7. 221869
    Prev
    Next
    INDEX
    Explanations

    cleaning, condition, routine, or preparation

    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
     درون
    0.43
    RELL
    0.42
    認識
    0.42
    rell
    0.40
     لهم
    0.39
    敢
    0.38
    昱
    0.38
    !:
    0.38
     نيك
    0.38
    འ
    0.38
    POSITIVE LOGITS
    ¨
    0.42
     given
    0.41
     condicion
    0.40
     cleaned
    0.40
    脏
    0.39
     condición
    0.39
     scrub
    0.39
     lilac
    0.38
     prepared
    0.38
     limpar
    0.38
    Activations Density 0.378%

    No Known Activations