© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3970
    Prev
    Next
    INDEX
    Explanations

    movement and data patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     සී
    1.22
     वगैरह
    1.22
    쾺
    1.21
     cá
    1.15
    subfigure
    1.12
     உட்பட
    1.10
     declare
    1.09
    …)
    1.08
    とか
    1.04
    ayvachi
    1.04
    POSITIVE LOGITS
    It
    1.18
    An
    1.11
    1
    1.05
    For
    1.03
    If
    1.02
    to
    1.02
    Providing
    1.00
    ă
    0.97
    The
    0.96
    inated
    0.96
    Activations Density 0.474%

    No Known Activations