© 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. 221862
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    if especially enab<b>ling</b>

    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
    Bounds
    0.52
    _
    0.48
    로
    0.48
    ch
    0.45
    atts
    0.45
    及
    0.44
    0
    0.44
    сад
    0.43
    .+
    0.43
    eva
    0.43
    POSITIVE LOGITS
     น้อง
    0.54
     အမျိုး
    0.53
     Сьогодні
    0.52
     comunicaciones
    0.51
     Infinix
    0.51
     Надо
    0.51
     периода
    0.51
     προϊ
    0.51
     Einwill
    0.51
     Время
    0.51
    Activations Density 0.000%

    No Known Activations