© 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. 1283
    Prev
    Next
    INDEX
    Explanations

    absurdism

    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
    ishops
    1.22
    asiun
    1.14
    campo
    1.10
     따르면
    1.08
     Sgt
    1.07
     최대
    1.06
    ittarius
    1.05
     '-'
    1.05
    propan
    1.04
    படுத்த
    1.04
    POSITIVE LOGITS
    َل
    1.00
    Herkese
    0.98
     بهذه
    0.96
    َم
    0.94
    َد
    0.93
    ْل
    0.93
     لم
    0.92
    해가
    0.91
    ماً
    0.88
     satisfactorily
    0.86
    Activations Density 0.581%

    No Known Activations