© 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. 4876
    Prev
    Next
    INDEX
    Explanations

    checking for null or empty

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

    return None or null

    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
    👱
    0.38
    ፦
    0.37
    嵩
    0.37
     অন্
    0.36
    olybdenum
    0.36
    杽
    0.36
     चर्च
    0.36
     vertebr
    0.36
    俭
    0.35
    耠
    0.35
    POSITIVE LOGITS
     null
    3.63
    null
    3.61
     NULL
    3.13
    NULL
    3.08
    Null
    3.02
     Null
    2.95
     nul
    2.69
     nulle
    2.56
     nullptr
    2.53
    nullptr
    2.44
    Activations Density 0.028%

    No Known Activations