© 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. 7375
    Prev
    Next
    INDEX
    Explanations

    numbers and time durations

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

    time ranges and quantities

    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
     þat
    0.22
    𝘞
    0.19
    সঙ্ঘ
    0.19
     препарата
    0.19
     वनस्पती
    0.19
     animaux
    0.19
     фармацев
    0.19
    <unused54>
    0.18
    যানী
    0.18
    货物
    0.18
    POSITIVE LOGITS
    0.30
    1
    0.25
    3
    0.23
    5
    0.23
     months
    0.22
    five
    0.21
     five
    0.21
    一个月
    0.21
    2
    0.21
    o
    0.20
    Activations Density 1.064%

    No Known Activations