© 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. 12635
    Prev
    Next
    INDEX
    Explanations

    multi- followed by a descriptor

    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
    ēj
    2.75
    િક્ષ
    2.71
    چی
    2.59
    te
    2.44
    ly
    2.39
    larından
    2.30
    ا
    2.28
    nee
    2.27
    short
    2.26
    ھی
    2.25
    POSITIVE LOGITS
    गी
    3.09
    𝘩
    2.74
    ऊदी
    2.58
    getExtension
    2.48
    ircon
    2.44
    gono
    2.43
    Absent
    2.42
    бен
    2.42
     hydrogens
    2.41
    Geplaatst
    2.37
    Activations Density 0.023%

    No Known Activations