© 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. 63729
    Prev
    Next
    INDEX
    Explanations

    kinda like or of

    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
    ي
    0.66
    י
    0.66
     différence
    0.63
    ت
    0.62
    i
    0.58
     bahut
    0.58
    X
    0.55
    y
    0.55
    ك
    0.55
    G
    0.55
    POSITIVE LOGITS
    ைகளின்
    0.55
     swirling
    0.52
    ைகள்
    0.51
    ங்களின்
    0.49
    landı
    0.49
     επίσης
    0.49
    ியோ
    0.49
     ανα
    0.48
    <unused330>
    0.48
    }']
    0.48
    Activations Density 0.040%

    No Known Activations