© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1892
    Prev
    Next
    INDEX
    Explanations

    job application and investigation language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chunks
    0.82
     pä
    0.78
     robi
    0.77
     trochu
    0.76
     selfishness
    0.76
     zrobi
    0.75
     messing
    0.75
    ẻ
    0.74
     bling
    0.74
     भागों
    0.73
    POSITIVE LOGITS
     proposals
    0.99
     probing
    0.98
     investigating
    0.97
     candidate
    0.95
     investigation
    0.94
     candidato
    0.94
    Candidate
    0.94
     proposal
    0.93
     investigate
    0.92
     Proposal
    0.91
    Activations Density 0.202%

    No Known Activations