© 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. 7908
    Prev
    Next
    INDEX
    Explanations

    launch related activities

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

    product and app launches

    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
     ഒഴി
    0.42
     ഒഴ
    0.41
     ਸੁ
    0.37
     erled
    0.36
    拄
    0.36
     অবন
    0.36
    酥
    0.36
     Rae
    0.35
    꺽
    0.35
     चक
    0.34
    POSITIVE LOGITS
     launch
    4.75
    launch
    4.53
     Launch
    4.38
    Launch
    4.28
     launching
    4.22
     launches
    4.16
     launched
    4.09
    Launching
    3.95
    launched
    3.95
     लॉन्च
    3.91
    Activations Density 0.199%

    No Known Activations