© 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. 2664
    Prev
    Next
    INDEX
    Explanations

    obtained, issued, or delivered items

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

    produced or delivered

    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
    めている
    0.49
     만드는
    0.47
    നുള്ള
    0.45
    sending
    0.44
    ributing
    0.44
    Sending
    0.44
     Producing
    0.44
    ⵖ
    0.42
     அதிகரிக்கிறது
    0.42
     பயன்படுத்து
    0.42
    POSITIVE LOGITS
     obtained
    1.42
     issued
    1.40
     delivered
    1.38
     submitted
    1.35
     released
    1.26
     procured
    1.24
     produced
    1.23
     получен
    1.23
     taken
    1.20
     received
    1.20
    Activations Density 0.456%

    No Known Activations