© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8010
    Prev
    Next
    INDEX
    Explanations

    bash scripts and specific terms

    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
     xây
    0.87
     Retrieved
    0.80
     T
    0.80
    Collapse
    0.74
     चले
    0.72
     il
    0.70
     Decentral
    0.68
     ru
    0.68
     cadre
    0.66
    建
    0.66
    POSITIVE LOGITS
     mentioning
    1.32
     insofar
    1.29
     wishing
    1.18
     surpassing
    1.16
     manifesting
    1.15
     whose
    1.15
     which
    1.14
     representing
    1.13
     amounting
    1.13
     pretending
    1.13
    Activations Density 0.003%

    No Known Activations