© 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. 190396
    Prev
    Next
    INDEX
    Explanations

    entry, necessary, outside, personal

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

    gravity and core

    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
     sparsely
    0.41
    {
    0.40
     sixteenth
    0.40
     poslov
    0.39
    計劃
    0.38
     lone
    0.38
    弟子
    0.38
     seventeenth
    0.38
    র্যের
    0.38
    锏
    0.37
    POSITIVE LOGITS
     אוי
    0.48
    મના
    0.47
     अमाव
    0.46
    פא
    0.46
     መንገድ
    0.45
    ֜
    0.45
     brut
    0.45
    <unused37>
    0.44
     FEST
    0.44
    פּ
    0.44
    Activations Density 0.000%

    No Known Activations