© 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. 227430
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     poles
    0.42
     sovereign
    0.41
     quadrants
    0.41
     goddesses
    0.41
    −
    0.40
     [];
    0.40
     buts
    0.40
    cede
    0.39
    いきます
    0.39
     guardians
    0.39
    POSITIVE LOGITS
     è
    0.53
     রাসূল
    0.53
     ហើយ
    0.52
     อีก
    0.51
     загру
    0.49
    ómago
    0.49
    inizio
    0.48
     Và
    0.47
     và
    0.46
    initis
    0.46
    Activations Density 0.002%

    No Known Activations