© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11582
    Prev
    Next
    INDEX
    Explanations

    positive and negative sentiment

    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
    )(
    2.36
    싹
    2.25
    q
    2.20
    γι
    2.16
    hurst
    2.12
    넣
    2.11
    입니다
    2.10
    arks
    2.09
    για
    2.09
    =?
    2.08
    POSITIVE LOGITS
    𝗶
    2.52
    ters
    2.43
    𝘀
    2.37
    𝗮
    2.37
    তনাম
    2.29
    𝘁
    2.27
    𝗲
    2.23
    𝗿
    2.18
    𝗢
    2.09
    nement
    2.09
    Activations Density 0.002%

    No Known Activations