© 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. 8135
    Prev
    Next
    INDEX
    Explanations

    active verbs on objects

    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
     आणि
    0.61
    性和
    0.58
     અને
    0.57
     ແລະ
    0.57
    度和
    0.55
    했고
    0.55
     և
    0.54
     없고
    0.54
     మరియు
    0.53
     거고
    0.52
    POSITIVE LOGITS
     aceste
    0.44
    ใน
    0.42
     polyurethane
    0.42
     ntawm
    0.42
    といった
    0.41
     această
    0.41
     các
    0.41
     dieser
    0.40
     importantly
    0.40
     także
    0.40
    Activations Density 0.170%

    No Known Activations