© 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. 166291
    Prev
    Next
    INDEX
    Explanations

    noun phrases followed by common determiners

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

    captivating descriptive writing

    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
    बर्ट
    0.51
    يط
    0.50
     atthakath
    0.50
    ر
    0.49
    幸福
    0.48
    呷
    0.48
    CipherText
    0.48
    胥
    0.48
     hMut
    0.48
    بعد
    0.47
    POSITIVE LOGITS
    vision
    0.45
     기
    0.43
    connect
    0.43
    pneum
    0.42
    (
    0.42
    )"
    0.42
    shorts
    0.42
     )
    0.41
    phenoxy
    0.41
    scar
    0.41
    Activations Density 0.000%

    No Known Activations