© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 20814
    Prev
    Next
    INDEX
    Explanations

    but then

    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
     ዓ
    0.45
    phys
    0.43
    😭😭
    0.42
    ोबर
    0.42
     บริ
    0.40
     physically
    0.40
    ᅴ
    0.40
     zahrani
    0.39
     miR
    0.39
     LOCCTR
    0.39
    POSITIVE LOGITS
     želite
    0.45
    荷兰
    0.40
    țial
    0.39
     đựng
    0.39
     Buttons
    0.38
     tắc
    0.38
    蛲
    0.38
     góc
    0.38
     Formatting
    0.37
     Button
    0.37
    Activations Density 0.024%

    No Known Activations