© 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. 55501
    Prev
    Next
    INDEX
    Explanations

    timelines, history, point, never

    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
     Weld
    0.47
     لفظ
    0.46
    為
    0.46
     dingen
    0.45
    ަށް
    0.43
     Wissenschaft
    0.43
     الكون
    0.42
     ஆழ்
    0.42
     المكتب
    0.42
    選擇
    0.41
    POSITIVE LOGITS
    igu
    0.48
     panc
    0.47
    oyote
    0.46
    ]【
    0.45
    ussie
    0.45
    aph
    0.44
    ern
    0.44
    xture
    0.43
    $/.
    0.43
    ecake
    0.43
    Activations Density 0.004%

    No Known Activations