© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29770
    Prev
    Next
    INDEX
    Explanations

    brakes and braking actions

    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_31_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
     pracowników
    0.44
     접속
    0.43
    whitelist
    0.42
     株
    0.42
    कार्यक्रम
    0.42
    代謝
    0.41
     कार्यकार
    0.41
     prosperity
    0.41
     বিদ্রোহ
    0.40
     uprising
    0.40
    POSITIVE LOGITS
     brake
    1.00
     braking
    0.94
     brakes
    0.87
    brake
    0.86
     Brake
    0.82
     freno
    0.71
     тормо
    0.70
    刹
    0.68
    brak
    0.66
     brak
    0.65
    Activations Density 0.023%

    No Known Activations