© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3529
    Prev
    Next
    INDEX
    Explanations

    technical terms and numbers

    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_16_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
     mcg
    0.51
     hearts
    0.48
     yeasts
    0.47
     histidine
    0.46
     woes
    0.46
     %}
    0.46
     prayed
    0.45
     Equation
    0.45
     blouses
    0.45
     dau
    0.44
    POSITIVE LOGITS
    d
    0.84
    ä
    0.75
    dü
    0.66
    é
    0.63
    g
    0.61
    ü
    0.60
    л
    0.58
    지
    0.58
    dienst
    0.56
    ആര്‍
    0.55
    Activations Density 0.192%

    No Known Activations