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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1463
    Prev
    Next
    INDEX
    Explanations

    version numbers and latest releases

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

    .org websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
     Trichodesmium
    0.32
    ())),
    0.32
    ын
    0.30
    VSLU
    0.30
    ())->
    0.29
    <unused72>
    0.29
    selfobj
    0.29
     PDPN
    0.29
    InData
    0.28
     ফেল
    0.28
    POSITIVE LOGITS
    |^
    0.37
     latest
    0.35
    npm
    0.34
     "^
    0.33
    latest
    0.32
    vana
    0.29
     conjunction
    0.29
     tv
    0.28
     Conj
    0.28
     Latest
    0.28
    Activations Density 0.025%

    No Known Activations