© 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. 5158
    Prev
    Next
    INDEX
    Explanations

    looking for

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

    problems and solutions

    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
    ("--------
    0.43
     нему
    0.40
     esforços
    0.38
     constitu
    0.38
     conceivably
    0.37
    =("
    0.37
     dónde
    0.37
    ("$
    0.36
    |"
    0.36
    ைகளைக்
    0.36
    POSITIVE LOGITS
     https
    0.40
    iliate
    0.37
     Ubuy
    0.37
    或者是
    0.36
     Clicking
    0.36
     Nullam
    0.35
     เว
    0.35
     Moovit
    0.35
    ⁤
    0.35
     ।
    0.34
    Activations Density 0.119%

    No Known Activations