© 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. 204233
    Prev
    Next
    INDEX
    Explanations

    calculating or desiring

    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
     [],
    0.50
     Capitalism
    0.49
     []*
    0.48
     Dracula
    0.46
     TabLayout
    0.46
    [],
    0.46
     Modelling
    0.45
     भाष
    0.45
     dharm
    0.45
     ensembles
    0.45
    POSITIVE LOGITS
    protein
    0.51
    IT
    0.49
    strength
    0.46
    GAN
    0.45
    न
    0.44
    IN
    0.44
    crest
    0.43
    -
    0.43
    ON
    0.43
    군
    0.42
    Activations Density 0.001%

    No Known Activations