© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2125
    Prev
    Next
    INDEX
    Explanations

    relying on

    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
    ea
    4.52
    ੀ
    4.16
    ej
    4.05
    e
    4.04
    een
    3.98
    tog
    3.87
    tens
    3.86
    t
    3.85
    eo
    3.82
    iendo
    3.80
    POSITIVE LOGITS
    ྒྱ
    2.86
    র্গে
    2.67
    𝕚
    2.59
    ాలు
    2.59
    cons
    2.58
    ქვს
    2.48
    ational
    2.44
    昧
    2.40
    substack
    2.38
    ient
    2.37
    Activations Density 0.231%

    No Known Activations