© 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. 2840
    Prev
    Next
    INDEX
    Explanations

    REMEMBER, how can, XX chromosomes

    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
    dct
    1.20
    CAP
    1.19
    MACl
    1.18
    sas
    1.16
    DEFGHIJKLMNOP
    1.15
    Logic
    1.15
    溉
    1.14
    DOS
    1.14
    ați
    1.14
    Sx
    1.14
    POSITIVE LOGITS
    কের
    1.16
    ীরের
    1.06
    아
    1.05
    نوان
    1.03
    ِه
    1.01
    neau
    1.01
    ously
    1.00
     زخم
    1.00
    '
    0.99
     anv
    0.99
    Activations Density 0.000%

    No Known Activations