Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 5787
    Prev
    Next
    INDEX
    Explanations

    stolen items, data, or currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    on
    1.01
    was
    1.01
    ра
    0.95
    r
    0.92
    ar
    0.89
    un
    0.89
    ran
    0.88
    ब
    0.87
    he
    0.86
    ре
    0.84
    POSITIVE LOGITS
     thefts
    1.43
     theft
    1.39
     steal
    1.21
     stealing
    1.20
     stolen
    1.20
     steals
    1.17
     stole
    1.11
     চুরি
    1.09
     thief
    1.07
    盗
    0.98
    Activations Density 0.020%

    No Known Activations