© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 52437
    Prev
    Next
    INDEX
    Explanations

    allocation, deallocate, release

    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
     تغ
    0.51
    risch
    0.50
     pleases
    0.50
     vlast
    0.49
     配
    0.49
    ılan
    0.48
    랐
    0.48
    事实
    0.46
    lara
    0.46
    ilig
    0.45
    POSITIVE LOGITS
     Dopo
    0.47
    ้ำ
    0.46
    OEM
    0.45
    uevo
    0.44
    SLAM
    0.44
    อยาก
    0.43
     După
    0.42
    ก
    0.42
     Quando
    0.42
     Gitar
    0.42
    Activations Density 0.006%

    No Known Activations