© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3508
    Prev
    Next
    INDEX
    Explanations

    unethical, unsafe conditions

    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_17_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
     thereon
    0.63
     asimismo
    0.62
     thus
    0.60
     тако
    0.59
    Trajectory
    0.59
     thereby
    0.57
     geodesic
    0.57
    杈
    0.57
     FURTHER
    0.57
    hede
    0.56
    POSITIVE LOGITS
     unethical
    0.84
    不能
    0.82
     stressful
    0.80
     માત્ર
    0.78
     केवळ
    0.78
     shouldn
    0.77
     unsafe
    0.76
    不上
    0.76
     不能
    0.75
     unhappy
    0.75
    Activations Density 0.338%

    No Known Activations