© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14670
    Prev
    Next
    INDEX
    Explanations

    hypo- or hyper- conditions

    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
     \
    2.56
     }{\
    2.47
    ெல்லி
    2.42
    a
    2.39
    כון
    2.35
    living
    2.33
    elmi
    2.21
    lade
    2.18
    ின்றது
    2.18
    l
    2.17
    POSITIVE LOGITS
    𝗲
    2.67
    𝗿
    2.62
    六
    2.47
    𝘁
    2.42
    вов
    2.40
    अमेर
    2.39
    𝘀
    2.33
    फ़
    2.32
    𝗹
    2.32
    istik
    2.30
    Activations Density 0.012%

    No Known Activations