© 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. 69709
    Prev
    Next
    INDEX
    Explanations

    negation or specific verbs after be/not

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

    maintaining stability

    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
     IBA
    0.55
    اه
    0.54
    แจ้ง
    0.50
     OOP
    0.50
    वीपी
    0.49
     ASA
    0.48
     PSU
    0.48
    ➧
    0.48
    िकुलर
    0.47
     vå
    0.47
    POSITIVE LOGITS
    tar
    0.51
    li
    0.50
    dur
    0.50
    moins
    0.49
    todos
    0.49
    repos
    0.48
    britann
    0.47
    sulf
    0.46
    dated
    0.45
    sum
    0.45
    Activations Density 0.000%

    No Known Activations