© 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. 201095
    Prev
    Next
    INDEX
    Explanations

    table schema access

    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
    sentence
    0.46
     incorporating
    0.43
    )$
    0.42
    incorporated
    0.42
    Mile
    0.42
    <0x0D>
    0.42
     magically
    0.42
    сре
    0.42
     WorldCat
    0.42
    values
    0.41
    POSITIVE LOGITS
     엄
    0.53
     nariz
    0.50
     실패
    0.50
     nause
    0.47
    엄
    0.46
    过于
    0.46
     பாதிக்க
    0.45
     인터넷
    0.44
     rusak
    0.44
     लगता
    0.44
    Activations Density 0.004%

    No Known Activations