© 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-65K
    7. 30141
    Prev
    Next
    INDEX
    Explanations

    speeches and phrases

    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
     (
    0.68
     এরূপ
    0.59
     "
    0.58
     hitherto
    0.58
     putative
    0.57
     “
    0.54
     envisaged
    0.54
     Thus
    0.54
     {\
    0.54
     ("
    0.53
    POSITIVE LOGITS
     साल
    0.63
     buscan
    0.63
     dicen
    0.59
     veulent
    0.58
    䟺
    0.57
     says
    0.55
    이죠
    0.55
     zegt
    0.55
     zeggen
    0.55
    這裡是
    0.55
    Activations Density 0.018%

    No Known Activations