© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11125
    Prev
    Next
    INDEX
    Explanations

    describing feelings and atmospheres

    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_7_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
    હીં
    2.47
    जिटिव
    2.37
    ﻡ
    2.30
    銈
    2.25
    쨔
    2.22
    𝐊
    2.21
    倰
    2.19
    烈
    2.19
    ئه
    2.18
    체가
    2.14
    POSITIVE LOGITS
    ு
    1.96
    링
    1.90
    ҽ
    1.84
    ქვს
    1.82
    ING
    1.80
     counter
    1.77
     Counter
    1.72
    Tact
    1.71
    led
    1.68
    tact
    1.68
    Activations Density 0.026%

    No Known Activations