© 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. 13783
    Prev
    Next
    INDEX
    Explanations

    phrases like timeframe than, next generation, control of

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

    lower and higher values

    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
    attered
    0.45
    atem
    0.43
     Heating
    0.41
     भएको
    0.41
     ♡
    0.40
    iamiento
    0.40
    qm
    0.39
    begin
    0.39
    ]<?
    0.39
     :
    0.38
    POSITIVE LOGITS
     Türkei
    0.50
     Kreuz
    0.48
     dafür
    0.46
     pretentious
    0.46
     pictureBox
    0.45
     Byzant
    0.45
     giapp
    0.45
    কর্ণ
    0.45
    یم
    0.45
    ताब
    0.45
    Activations Density 0.000%

    No Known Activations