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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 224309
    Prev
    Next
    INDEX
    Explanations

    fragments of words

    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
     」,
    0.43
     sangue
    0.41
     Forming
    0.41
     Retry
    0.38
     Đó
    0.38
     immunotherapy
    0.38
     Ψ
    0.38
     혈
    0.37
     João
    0.37
     clínica
    0.37
    POSITIVE LOGITS
    c
    0.47
    كن
    0.46
    cha
    0.44
    차
    0.44
    য়ের
    0.44
    cou
    0.43
    e
    0.42
    enem
    0.42
    ives
    0.40
     decena
    0.40
    Activations Density 0.001%

    No Known Activations