© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52194
    Prev
    Next
    INDEX
    Explanations

    comparison, degree, state

    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
    اض
    0.44
     !!,
    0.40
    পুন
    0.40
     మీ
    0.39
    ే
    0.39
    !!.
    0.39
    乗
    0.39
     añad
    0.38
     найбіль
    0.38
    ض
    0.38
    POSITIVE LOGITS
    mere
    0.42
    kes
    0.42
     substandard
    0.42
    centric
    0.41
     upfront
    0.41
    rica
    0.41
     دائما
    0.40
     hasil
    0.40
     רק
    0.40
     Jamal
    0.40
    Activations Density 0.001%

    No Known Activations