© 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. 7649
    Prev
    Next
    INDEX
    Explanations

    socialist republic, neighbour, lair

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

    languages and linguistics

    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
     apabila
    0.45
     Согласно
    0.45
    喺
    0.44
     మరియు
    0.43
     তথাপি
    0.42
     како
    0.41
    Whilst
    0.41
     Whilst
    0.41
     продол
    0.40
    更加
    0.40
    POSITIVE LOGITS
    ŏ
    0.54
     vei
    0.53
     къ
    0.53
     nombr
    0.50
    ôs
    0.49
     vun
    0.48
     egent
    0.47
    <0xEA>
    0.47
     pued
    0.47
     dź
    0.47
    Activations Density 0.007%

    No Known Activations