© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13445
    Prev
    Next
    INDEX
    Explanations

    topics not involving harmful content

    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
    factorial
    1.78
    DFLAGS
    1.72
    şam
    1.67
    नल
    1.66
    ﮧ
    1.65
    шай
    1.65
    AndUpdate
    1.63
    spě
    1.62
     gsap
    1.60
    isComposite
    1.58
    POSITIVE LOGITS
     gồm
    1.44
     ED
    1.39
     არ
    1.38
    แด
    1.37
     units
    1.34
     back
    1.34
     pacing
    1.32
     through
    1.31
     จาก
    1.30
    ─
    1.30
    Activations Density 0.073%

    No Known Activations