© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10155
    Prev
    Next
    INDEX
    Explanations

    brutal honesty

    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
    Negative Logits
     przyj
    2.56
    Downloaded
    2.46
    bbene
    2.44
    menes
    2.40
    uhan
    2.32
    ITECTURE
    2.32
     Fig
    2.25
    ruk
    2.24
    ▌
    2.22
     Schon
    2.20
    POSITIVE LOGITS
    тні
    2.40
    arzys
    2.21
    SSE
    2.20
    ებლ
    2.19
    lois
    2.18
    acids
    2.17
    াস্থ্যের
    2.16
    ิศ
    2.13
    srv
    2.12
    꼴
    2.12
    Activations Density 0.013%

    No Known Activations