© 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. 30500
    Prev
    Next
    INDEX
    Explanations

    discusses tales and origins

    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
     nėra
    0.46
     превы
    0.44
     queremos
    0.44
     aforementioned
    0.42
     selfless
    0.41
    前来
    0.41
     comandante
    0.41
    徬
    0.41
     اعز
    0.40
     calmed
    0.40
    POSITIVE LOGITS
     Alive
    0.41
     ভবিষ্যত
    0.41
     New
    0.38
    atorio
    0.38
    riculum
    0.37
     Lifetime
    0.37
     Zugang
    0.36
     Universal
    0.35
    hava
    0.35
    get
    0.35
    Activations Density 0.019%

    No Known Activations