© 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. 13603
    Prev
    Next
    INDEX
    Explanations

    certification and transcription

    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
    м
    2.89
    ಿಂದ
    2.73
     casings
    2.72
    sapp
    2.65
    ோ
    2.62
    ऩे
    2.59
    ிர
    2.57
    ँच
    2.50
    로우
    2.48
    ේශ
    2.48
    POSITIVE LOGITS
    𝐞
    3.02
    𝐫
    2.68
    পূর্ন
    2.63
    ূট
    2.61
    dale
    2.60
    рур
    2.59
    𝐥
    2.58
    rael
    2.55
    itas
    2.53
    ৎস্য
    2.48
    Activations Density 0.002%

    No Known Activations