© 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-65K
    7. 15918
    Prev
    Next
    INDEX
    Explanations

    or alternatively

    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_65k_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
     tof
    0.44
    ievement
    0.44
     სწ
    0.43
    মিনা
    0.41
    定
    0.41
    तोष
    0.41
     solidify
    0.41
    tLogRow
    0.41
     paperwork
    0.41
     наиболее
    0.40
    POSITIVE LOGITS
    ě
    0.42
     কিংবা
    0.41
     or
    0.41
     Sew
    0.38
     oder
    0.38
    য়াস
    0.38
    ],
    0.37
    uv
    0.37
     alternatively
    0.37
    _{
    0.36
    Activations Density 0.029%

    No Known Activations