© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109773
    Prev
    Next
    INDEX
    Explanations

    reporting speech or reporting verbs

    np_acts-logits-general · gemini-2.5-flash-lite

    former dancer describing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ोन
    0.45
    낡
    0.43
    차
    0.42
    𝓰
    0.41
    ха
    0.41
    할
    0.41
    粎
    0.41
    귤
    0.40
    वा
    0.40
    受到了
    0.40
    POSITIVE LOGITS
     mengatakan
    0.52
     comentó
    0.49
     dijo
    0.48
     says
    0.46
     exclaimed
    0.45
     menambahkan
    0.45
     quería
    0.44
     sedangkan
    0.44
     decided
    0.43
     sagte
    0.43
    Activations Density 0.025%

    No Known Activations