© 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-262K
    7. 22720
    Prev
    Next
    INDEX
    Explanations

    as a comparison

    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_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
     mucha
    0.46
     لیا
    0.45
    ControlEvents
    0.44
     desemb
    0.44
     នៅ
    0.44
     বিষ্ণ
    0.44
    dan
    0.43
    铣
    0.43
     Tried
    0.42
     Cannot
    0.42
    POSITIVE LOGITS
     violation
    0.49
     divergence
    0.45
     neutrality
    0.45
     throat
    0.44
     alkaline
    0.44
     prote
    0.43
     prostaglandins
    0.43
     doubling
    0.42
    Nation
    0.42
     summation
    0.42
    Activations Density 0.001%

    No Known Activations