© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3396
    Prev
    Next
    INDEX
    Explanations

    apostle or apostles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    h
    1.16
    et
    1.12
    ?
    1.10
    ah
    1.08
    ed
    1.02
    on
    1.00
    ро
    0.96
    ens
    0.96
    v
    0.95
    en
    0.95
    POSITIVE LOGITS
    یر
    0.91
     apostle
    0.86
    циям
    0.84
    การ
    0.80
    )：
    0.78
     Apostles
    0.77
    ಧಾರವಾಡ
    0.77
     disciples
    0.76
    ことに
    0.75
    PACK
    0.75
    Activations Density 0.001%

    No Known Activations