© 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. 61245
    Prev
    Next
    INDEX
    Explanations

    liquid phase, tempting target, safe trip

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

    used to, disturbed, generate data, wall jump

    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
    komst
    0.46
    JM
    0.46
    etz
    0.43
    λεσμα
    0.43
    слан
    0.43
    ל
    0.41
    意
    0.41
    IS
    0.41
    Semit
    0.40
    מיד
    0.40
    POSITIVE LOGITS
     형태
    0.58
     শতাংশ
    0.54
     আবদুল্লাহ
    0.52
     tantôt
    0.51
     데이터를
    0.51
     lokasi
    0.48
     fetchData
    0.48
     remport
    0.47
     Dokl
    0.47
     determ
    0.46
    Activations Density 0.001%

    No Known Activations