© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13402
    Prev
    Next
    INDEX
    Explanations

    respectively, former, latter, each

    np_acts-logits-general · gemini-2.5-flash-lite

    former, latter, respectively, both

    np_acts-logits-general · gemini-2.5-flash-lite

    period

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
    onnen
    0.39
     এটির
    0.38
     its
    0.38
     അതിന്റെ
    0.37
    ╤
    0.36
     इट्स
    0.36
    庐
    0.35
    ;&
    0.35
     അയാള
    0.35
    因为它
    0.34
    POSITIVE LOGITS
    前者
    1.52
    それぞれ
    1.09
     각각
    1.01
     keduanya
    1.00
    后者
    1.00
     latter
    0.91
    respectively
    0.91
     begge
    0.87
     beide
    0.86
     respectively
    0.86
    Activations Density 0.440%

    No Known Activations