© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14332
    Prev
    Next
    INDEX
    Explanations

    at [place name]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    ോധ
    2.27
    ƌ
    2.27
    ぞ
    2.26
    ale
    2.25
    ঙালি
    2.20
    с
    2.18
    कुंठ
    2.16
    友好
    2.06
    ikation
    2.05
    ပျ
    2.03
    POSITIVE LOGITS
    ר
    2.53
    batch
    2.51
    כו
    2.43
    mind
    2.39
    क्षेप
    2.35
    ल
    2.33
     denke
    2.31
    ﻒ
    2.30
     Saying
    2.29
    rass
    2.26
    Activations Density 0.049%

    No Known Activations